ch · context-v
Context-V
Specs, explorations, plans, prompts, and reminders across the ai-labs tree. Parent-authored docs live alongside the rolled-up child docs; provenance is on every card.
specs59explorations59plans66prompts9blueprints15reminders15issues62issue-resolution2sitemap29context-v203
specs59
augment-it SearchBox — LiveFilter and Autocomplete
A subsidiary spec. Two named variants over one private core, because the keyboard contract must exist exactly once and the two differ only in where options come from.
augment-it The component API contract and the control scale — inspired by shadcn, with sprinkles of Tailwind, derived from what members already built
Members were already converging on Tailwind's radius scale by instinct. They just had no token to spell it with.
augment-it Design System Convergence — the organ registry, its five verdicts, and the fingerprint ledger that catches drift while it happens
The registry is what makes drift legible: a declared organ is a decision, an undeclared one is drift. The code can be identical in both cases.
corpora-builder Header Chrome
The workspace becomes a switcher, not a label. The mode toggle shows one icon and says what the next click gets you.
corpora-builder Ranked Search — Pagefind over the manifest
Substring matching cannot rank, stem, or take two words in any order. Pagefind can. It indexes the manifest, and never replaces it.
corpora-builder Search Index — the manifest that stops search reading the corpus
A search opens every file: 845 reads, up to 5.8 seconds. A manifest in the corpus makes it one, and closes the gap FOCUS-07 named.
corpora-builder Strategy Focus
A strategy chip narrows the list and compounds with search. The corpus count rides alongside, so a subset always says what it is a subset of.
ai-labs id.didi.sh — the Didi Identity Service
One owned identity service: headless-first API, a signed session cookie on `.didi.sh`, invite-only accounts — built on Elixir/Phoenix.
corpora-builder Binary Ingest and the bin/ Store — one copy, optimized, fetched on demand
78 files are 90.5% of the corpus bytes. Compress once, store once by hash, fetch when asked, delete locally without fear.
corpora-builder Corpus Change Feed — what changed in a client's corpus, and why
A change record any history engine can emit, and a feed that renders it for someone who will never read a diff.
corpora-builder Corpus Tree
A corpus is a folder the client can't see. The tree is built from keys alone, so showing 944 files costs zero reads.
corpora-builder Domain Navigation
112 folders in a dropdown is a list you scroll, not a list you use. Type any near-match; backspace walks back a segment at a time.
flave Flave — An Agent-Native Document Format and Desktop Publisher
The master spec. A package format (.flave) and an editor built on Lossless Flavored Markdown — a document that keeps its workings, publishes only what you choose, and is written in the languages agents already speak fluently.
augment-it Federated Component Libraries
One gallery runtime, seventeen sovereign catalogs — every member publishes what it is made of, at its own address.
corpora-builder Browse Corpus — a screen for the work that already exists
The first surface: read-only over reach-edu's 892 existing files. Pulled out of Phase 7 because Tauri was never the cheapest first screen.
corpora-builder Capture From The Screen — the surface stops being a viewer
Paste a URL and watch it get filed. Writing is opt-in at the server (`--writable`) because the first corpus this screen saw was a client's.
corpora-builder Capture, Link-First — the first command that pays for itself
`corpora add <url>` fetches, names, dedupes, and files a link as a source — metadata-only by default, because bulk enrichment goes haywire.
corpora-builder Loop Harness — the ledger that lets an agent run unattended
Spec IDs bind to test functions, status is derived by running the suite, and a promise with no test is a build failure.
corpora-builder Source-File Model — the schema becomes code, and two silent failures become loud
The schema as a round-tripping dataclass — the stray `---` that hid 13 of ImmuneCo's 93 sources is now a hard error, not a silent one.
corpora-builder Storage Seam — one interface, three implementations, and the workspace that names the bucket
A CorpusStore over local, R2, and cache, proven by one conformance suite that runs against every backend with no test-side branching.
augment-it Source Content Storage — SurrealDB-Primary, Local as a Per-User Toggle
Flip the content store: the article body moves onto the canonical `sources` row and the local filesystem write demotes to a toggle.
context-vigilance-kit MVP: context-v as a Claude Code Plugin
The kit's MVP is not the Chroma memory system the June specs planned — it's a plugin where `/plugin install` is the whole onboarding.
augment-it Corpora Builder Harmony — the evolving test registry
Every proposed and implemented test guarding the corpora builder and the systems it must harmonize with — identity, workspace connector, transport, state, canonical layer, files — in human language, MECE, one ✓-phrase each.
augment-it Design System Portal
Specification for the portal that renders the federated design system — the swatch page, the token catalogue, the member index.
augment-it Federated Design System Architecture
The organising specification for augment-it's two-tier, seventeen-member design system.
augment-it Augment from DB — the Org Workbench + Search-and-Add flow: two new microfrontends over capabilities that mostly exist
Start from a canonical org, not a CSV row: an org workbench over links, streams, corpus and people, plus provider-pluggable search-and-add.
augment-it Entity-Card Edit & Remove Affordances — every visible property gets a micro-button pair
The org card views and edits in place, but only additively — a misclicked ➕ today required a direct database write to undo. Every entry and identity property the card shows grows ✎ and × micro-buttons.
augment-it Search-Results Queue — a right-rail microfrontend where concurrent agent searches land, signal, and get triaged
Agent searches run minutes; the operator shouldn't. Every search becomes a card in a persistent right rail — fire many, triage on arrival.
augment-it Connector Inventory & Per-Record Palette — Hot-Swap Providers, Re-Fire One Record at a Time
Per-record connector palette: click `f` to re-fire one row through the next Facebook provider, over a registry that resolves by capability.
augment-it Strategy Curator — An Entry-Point App for augment-it
A canonical source registry in SurrealDB owns identity, the client's filesystem owns usage, and a shared UUID is the only bond.
augment-it Entity-Pulse Bundle — Press Releases, News Mentions, and the Social Voice of a Record
Official Updates fires first; its rollup becomes the relevance prior for Media and Socials Mentions — a foundation-first four-phase DAG.
augment-it Pulse pattern — one operator burst against one entity, expressed as N independent pulse-dimensions composed in a pulse-surface, each dimension potentially owning its own microservice
Operators enrich in bursts, not steps: one search fills name, socials, emails, and org, and a pulse-surface commits all of it in one save.
augment-it Record ↔ DB Resolver — operator-driven match/create bridge from row-store records to canonical organizations
Row-store records and canonical SurrealDB orgs were never bridged; the resolver closes the gap one record at a time, operator driving.
augment-it Sparse-Person Enrichment Surface — per-email triage where the operator finds the human behind the address, picks or creates the org they belong to, and writes both back to the canonical layer
177 event attendees landed as 177 bare emails — the opposite shape from the URL-bearing records every other augment-it flow assumes.
augment-it Augment from Affiliations — the first flow that starts from SurrealDB instead of a CSV, turning an event's speaker/org pairs into a rated, sourced prospect list
The first flow that starts in the canonical layer, not a CSV: export an event's affiliations, rate relevance offline, reimport.
ai-labs The Source Curation Surface — A Component Architecture for a Svelte Rebuild
Decomposes a proven single-file curation tool into Svelte components: a runes store, a tree of small components, one API contract.
augment-it Workspaces as Tenant Primitive — toggling, tenant-aware microservices, per-tenant env-var pickup, and the seam that lets MCPs and connectors vary per client
`workspace` is the tenant boundary — humain-vc vs reach-edu. The vision is stated once, then step 1 is cut down to filesystem-only bones.
augment-it Client tagging on canonical writes — every observation carries the client that produced it, and every canonical entity carries the materialized set of clients that can see it
The canonical layer is cross-client by design — a materialized `client_access` array is how each workspace still sees only its own.
augment-it Records Surface sort step and UI — sort ships as part of the **Sort & Filter Lens**, the second lens in step 2's default set (alongside the existing **Pack Firing Lens**); `lens` is the architectural primitive this spec introduces and lenses are *swappable* (one active per step at a time), not stackable; each step ships with a small curated default lens set and the registry stays *open* so new lenses can join without architecture changes
Sort ships as the second swappable lens on step 2 — and the lens registry is open, so a new lens is a manifest drop, not an enum edit.
augment-it Chat Context-Awareness Architecture — three layers (workspace as context broker, slab-assembly contract, verb registry) that grow the in-app chat from prompt-only to surface-aware verb router
Chat's verb roster is a hand-written prose block and its context slab carries only `record_set_id`; this closes both holes.
augment-it Corpus Inbox — capture first, triage later; a zero-friction save destination for URLs without a home yet, with a future triage layer that sorts inbox content into the right places
A URL with no home yet shouldn't cost a filing decision: `corpus/inbox/` captures the page, its body, and a drive-by note, then waits.
augment-it Funder Content Corpus Workflow — what the system has to do, ranked by quality bar, with no implementation prescribed
Written so a future agent resists the pull to filter yesterday's bad data tighter instead of firing fresh for today's good data.
augment-it Record-Set Family Grouping — internal lineage vs. external-variant families in the Record Collector sidebar
The sidebar shows a tracker uploaded as v4–v8 as five unrelated CSVs. Two family kinds — promotion lineage and external variant — fix that.
augment-it Response Reviewer Shell and Content-Reader Mode — Response Reviewer becomes a wrapper whose inner review UI swaps based on what the bundle that fired actually produced
1,109 OfficialPulse responses, 3 accepts: 'is this URL right?' is the wrong question for content packs, so review mode becomes swappable.
augment-it Flow for Bundles & Packs — The Simplest Possible Thing
For 67 rows with a website URL, find each one's blog index. Two surfaces, no reviewers — this spec deliberately ignores the five before it.
augment-it Per-Record Iteration as the Primary Surface for Pack and Bundle Fires — The Flow Rearranges Per Fire Type
A pack fired across 96 rows returned 0 found — so per-record iteration becomes primary and bulk fan-out waits until a chain is proven.
augment-it Pulse Curation Layer & UI — Three Layers per Category, Triage Per Item, Finalize on Demand
Three layers per category: immutable `raw_output`, live `curated_output`, and a `finalized_output` snapshot locked when triage is done.
augment-it Shell & Micro-Frontend UX Coherence — Affordances That Are Found, Consistent, and Talk Back
A demo-prep chain of 'I can't find / reach / trigger X' is a verdict: the shell's affordances hide, die, or mismatch. Fix the pattern.
augment-it Tooltip System — A Versatile First-Class Family, Plus a Walkthrough for New and Returning Users
Apps fail at orientation, not functionality — so tooltips become a first-class family, not the browser's half-working `title=`.
context-vigilance-kit Commands and Agent Skills for context-v
Catalog of every command, slash command, and agent skill the kit ships — surfaced natively via `.claude/commands/` and `.claude/skills/`.
augment-it Enhanced Records List — the Triage Checkpoint and the Promotion Loop
One record-grained view of a whole enrichment round: select the good rows, promote them to canonical, and the predecessors archive.
augment-it Request Reviewer — the Pre-Flight Surface
See exactly what is about to leave the building — and guarantee the request you reviewed is byte-identical to the one that fires.
augment-it Response Reviewer and Response Store — the Post-Flight Surface
No review surface until a fired response is a first-class stored object — so response-store and response-reviewer are specced as one.
augment-it Walking-Skeleton Pre-Flight Decisions — Augment-It Rewrite
Five substrate decisions — state, transport, persistence, auth, agent scaffolding — settled before code so no session re-walks the tree.
augment-it Augment-It as a CRM-Augmentation Pipeline (Microfrontends + Microservices)
memopop makes memos, dididecks makes slides, augment-it makes information that lands back in a CRM it doesn't own.
ai-labs In-App Agent Chat — Core Package Spec
One package — capability registry, BYOK proxy contract, chat UI API, transcript schema — targeting web and Tauri, proven first on dididecks.
memopop-ai/memopop-orchestrator Introducing a Diagram Generator Agent
Add a diagram_generator.py agent that identifies opportunities to create visual diagrams explaining complex business concepts, starting with TAM/SAM/SOM market sizing and expanding to common finance and consulting visuals.
memopop-ai/memopop-orchestrator PDF Parser Agent Specification
A small specification for an agent and script to parse PDFs and convert them to markdown with properly formatted citations.
context-vigilance-kit context-vigilance-kit/specs/index
explorations59
ai-labs A Syncbox for Client Document Folders — Where Does History Actually Live?
The ask is one product. The prior art says it's three layers, and nothing on the shelf does all three on a bucket.
context-vigilance-kit Context-V as a Portable Plugin Any Agent Can Install
A human pastes one line, and their agent does the rest. The last mile of the cv plugin is an install contract written for agents, with Claude Code as the first harness, not the only one.
flave The MVP Delta, and What 'A Version Per Audience' Actually Requires
The editor half of the MVP is mostly built. The half that is the product, one document published to several audiences with proof that nothing leaked, has no code yet, two underspecified mechanisms, and one syntax in the spec that does not parse.
studies Explore Collaborator Codebases for Insights — Comparative Highlights
When a friend has built their own agentic-coding silo next to ours, compare the silos both ways: what we can learn from them, and what they can learn from us.
augment-it The Gap Between What We Preach and What We Practiced
Forty deployable units, one git repo, zero component-level design systems or changelogs. An honest audit of augment-it against the three recommendations we make to clients.
ai-labs didi.sh — One Login, One Agent, Three Services
memos, decks, and augment-it become one family coordinated by exactly two shared planes: a common identity service and one agent named didi. Consumer one is live; the local-auth question is now closed.
context-vigilance-kit Context-V as a Claude Code Plugin
The conventions are good and the agent still forgets them. A plugin turns context-v's workflows into commands and its frontmatter into queries — so a loop's preconditions get checked instead of remembered.
id-didi-sh What Corpora-Builder Needs From didi.sh — the primitives list, handed over early
corpora-builder wants workspace identity from didi.sh. Two gaps: workspaces aren't a thing here yet, and a CLI has nowhere to put a cookie.
memopop-ai Curating Only Valid Sources Across Runs
Downstream curation cannot fix what `citation_enrichment.py` invents upstream — 65 fabricated `example.com` URLs in a single run.
augment-it Design Language Audit — July 2026
The hand-counted baseline audit that measured the state of augment-it's CSS before the design system shipped. Superseded as the counting mechanism by design-drift.mjs.
ai-labs Secrets for Collaborators Who Will Never Open a Terminal
Collaborators who will never open a terminal still carry API keys — so serve capabilities from a remote MCP plane, secrets held server-side.
id-didi-sh Serving Secrets Server-Side as an MCP Capability Plane
Implementation-local notes on a remote MCP endpoint that holds credentials server-side and hands collaborators capabilities, not secrets.
augment-it Augment from DB — the org-first workbench flow, and the two new microfrontends it needs
A flow that starts from SurrealDB, not a CSV: pick an org, reveal its people and pulse streams, augment through pluggable search packs.
augment-it augment-it has outgrown one flow — ROTATION is the CSV-augmentation pipeline's shape wearing a general-purpose name, and corpora-curator's promotion to its head is a splice, not a fit
ROTATION (`shell/src/remotes.ts`) is the CSV-augmentation flow hardcoded as THE nav — every other use case gets spliced onto it.
corpora-builder Corpora-Builder System Design
Corpus building has been rebuilt as a sub-feature three times across ai-labs. This exploration surveys what those iterations actually taught us, and sketches the system that deserves its own repo.
corpora-builder Design Front-Loading and the Fable Build Loop
If frontier models can now carry complex builds end-to-end, the leverage moves to the documents. Can we front-load design so hard that the whole system gets built in a TDD loop — and impose design-system discipline from commit one?
augment-it Syncthing for Collaborator Access to the Corpus (R2 Backup Already Decided)
R2 already won the backup leg — rclone, not a live mount. This is the separate, still-open question: could Syncthing give other humans live access to the same corpus, without breaking the single-writer discipline that's kept things sane so far?
ai-labs Cross-Product Native Agent Shell — Synthesis and Architecture Decision
Resolves the fork the in-app-agent docs left open — extend memopop-native or build standalone — against sixteen pinned repos' actual source.
ai-labs In-App Agent Chat — As-Built vs. As-Specced (Internal Audit)
`@lossless/in-app-agent` was never built — augment-it inlined the WorkspaceAdapter pattern into `@augment-it/workspace` instead.
ai-labs Shared Auth for Applied AI Labs
Three sibling apps need login; none is at Auth0/Clerk scale. A small owned system: OAuth, invites, org-scoped roles, a roll-up seam.
ai-labs Two Clients, One Flow — Corpora by Domain-Type, Auth, and Deployment Converge
reach-edu wants corpus→memos by strategy, humain-vc by thesis — and typed domains, shared auth, and deployment all came due at once.
ai-labs Corpus-Grounded Generation — Memory & Graph Layers for Producing Decks and Memos Without Drift
A pipeline where every factual sentence in a deck or memo traces to a source span — and the model abstains when it can't.
augment-it The Moat Is Grounded Deliverable Production, Not Chat
Chat-over-documents is commoditizing; the moat is the last mile — a shippable deck or memo with every claim traceable to source.
augment-it Funder-Fit Engine — Org-Anchored Corpora and the Bidirectional Story↔Funder Cycle
Fundraising matches both ways — funder→story and story→funder — on one org-anchored corpus. The differentiator is KAG, not plain RAG.
augment-it Forced One-By-One Tag Selector — a pulse-dimension pattern for deliberate triage instead of lazy bulk-tick
Bulk checkboxes produce uniform half-considered tags. Present one tag at a time — apply / skip / skip-rest — and each decision gets made.
augment-it Joined People UI and the Network-First Pivot — augment-it's sibling-flow to org-first augmentation, and the canonical/proprietary layer split underneath it
Org-first and people-first are two pivots on one join — and the split that matters is canonical (shareable) vs proprietary (client-only).
augment-it Best Way to RAG Over the Corpus — design space for retrieval-augmented operations on augment-it's per-client corpus, given the structured frontmatter we just earned
245 corpus files carry `funder_slug` and `published_at`, so retrieval is facet-filter-first — embeddings handle the residual about-ness.
augment-it Inbox Sort by Agent Tasks — moving the inbox from a flat 86-item pending queue into a task-typed work surface where the operator sees what's next and the agent does the safe parts automatically
86 pending inbox files render identically, so the operator context-switches between four task types on every scroll.
augment-it Operator-built flows beyond the universal pipeline — the default augmentation path is a dud for most edge cases, and the cheaper-than-microfrontend escape is a view-spec the agent-chat composes from natural language and the UI renders generically
The default flow lands cleanly on 17 of 96 reach-edu records. The escape isn't a microfrontend per scenario — it's a generic spec-renderer.
memopop-ai Grill Me: A Per-Section User-Input Moment in MemoPop Runs
A pause-point where MemoPop grills the user — the competitive section's synthesis frame is a judgment the model shouldn't make alone.
augment-it In-App Browser vs Browser Plugin for Corpus Add — bridging the operator's own search into the per-record corpus without leaving the cockpit
Adding one operator-found URL to a funder's corpus is a ten-step round-trip out to Google and back. In-app browser, or browser plugin?
augment-it Per-Client Privacy and the Path Off Local — when does single-operator-local-only stop scaling, what stack do we reach for, and how do we architect today so the move is cheap when it comes
Per-client corpus privacy and a client wanting login hit the same week. Not a stack decision — which choices keep the move off local cheap.
ai-labs Cloud Variant of the Dididecks-AI Workspace — Recreating Local Privacy When the Filesystem Isn't Yours
Clients who won't install a desktop app still need the privacy local-fs gives for free. What a cloud runtime would have to do explicitly.
augment-it Agent-Chat Skills and Commands — Candidates List
The chat's verb roster is four prompt-focused capabilities. A running list of shell scripts that should graduate into chat-callable verbs.
augment-it Augment-It Prior Art Survey — What's Already Been Built, and What It Tells Us
Two prior attempts exist — Tanuj's three federated repos and Michael's bolt monolith. Both cover the core; neither is what we ship.
augment-it Bolt-Era API Provider Widget Analysis
The bolt widget picked Claude, GPT, or Perplexity per prompt section. The widget dies in the rewrite; the multi-provider shape stays.
augment-it Bolt-Era Codebase Analysis
A faithful architectural map of the bolt monolith — React + TS + Vite + Supabase + zustand — lifted from its own `specs/` folder.
augment-it Bolt-Era Highlight Collector Analysis
The only existing description of the highlight-collector stage — one of two that never got split into Tanuj's microfrontend repos.
augment-it Bolt-Era Main Container UI Analysis
The bolt shell's five-column layout and auth gate — prior art for the rewrite's open question: one host shell, or a host per app?
augment-it Bolt Monolith As Built — The archive/bolt-code Branch
The earliest augment-it is a Vite + React monolith on `archive/bolt-code`: feature-richer than the federated repos, architecture we discard.
augment-it Bolt-Era Prompt Section Analysis
Prompt templates as MDX-rich, variable-aware, edit-toggle-preview blocks — the pattern prompt-template-manager should probably adopt.
augment-it Bolt-Era Record Collector Analysis
Cross-reference against `Tanuj-Record-Collector-As-Built` — the diff between bolt-era and forked shows which patterns survived federation.
augment-it Entity-Profile Augmentation Workflow — Common Social + Vertical-Specific Sources, Per Entity Type
Two tiers replace prompt-by-prompt column filling: packs as atomic source-bound units, bundles as workflow-shaped compositions of packs.
augment-it Federation and Bundler Decision — Bun + Rsbuild + Module Federation, Workspace State, Optional Chat
We federate: Module Federation on rsbuild, bun over turbo, and state of truth in `@augment-it/workspace` — chat is just one consumer.
augment-it Tanuj's Prompt-Manager As Built
Full CRUD-shaped prompt UI over a hardcoded `samplePrompts` array — no store, no data flow. Keep the schema, throw away the implementation.
augment-it Tanuj's Record-Collector As Built
The most-finished of Tanuj's three splits. One idea survives: the prompt template auto-generates from the imported CSV's columns.
augment-it Tanuj's Request-Reviewer As Built — The Module Federation Proof
The only place Tanuj got federation working — a shared `RecordCard` — while the augmentation logic sits copy-pasted from record-collector.
memopop-ai Human-Curated Source Sets and Per-Firm RAG for Memo Narrative
Keep Perplexity's take as quarantined commentary and route real research through validated harvesters plus a per-firm standing RAG store.
augment-it Multi-Agent Research Fan-Out Per Row — The Real Shape of Augment-It's Capability Runtime
Capabilities aren't LLM calls — five research agents run per row in parallel, so the runtime needs (rows × agents) fan-out.
ai-labs Memory Layers for the In-App Chat Package
Maps the eight pinned memory systems onto roles in the chat package, and picks the v1 stack given we already lean on Chroma.
ai-labs Remote Mount Contract for @lossless/in-app-agent — How the Chat Surface Drives Federated Views Without Owning State
How the chat surface drives federated views without owning state: capability invocation goes through the per-app workspace, never the chat.
ai-labs In-App Chat as the Agent Surface for Client Apps
Rather than design a button for every client request, wire one chat surface loaded with our patterns and context. The chat is the menu.
memopop-ai Separating Retrieval from Generation in Agent Pipelines
An agent that both searches the web and writes the prose fabricates URLs — 65 `example.com` links in a single memo run.
ai-labs When Claud Code and When Pi
ai-labs ChromaDB as Context Improvement Across Everything, Everyone
A founding-team demo reframed Chroma: not a place to put embeddings, but an ingestion layer for agent traces and session transcripts.
ai-labs Collate Context Files into Context Vigilance as Repo & Project
A long-running, everywhere-distributed practice — context-v/ across a tree of pseudomonorepos — finally graduates into a project of its own, with a collator, a splash, and a vector index.
memopop-ai Crawl for Better Team Structured Output
The orchestrator writes prose about teams but never returns the structured roster the app needs to render cards: names, titles, photo URLs.
memopop-ai Moving an Agent Orchestrator to an API
The orchestrator is a Python CLI today. To plug it into memopop-native, we need an HTTP-shaped surface. Three options, ranked by effort and time-to-value.
context-vigilance-kit context-vigilance-kit/explorations/index
plans66
studies Analyze Harness-like Evidence in a Collaborator Codebase
Step 1 of 3: read a collaborator's repo for every sign of how they work with coding agents, and inventory it with paths and dates.
studies Compare and Contrast Harness-like Artifacts between Lossless and a Collaborator
Step 2 of 3: set our harness beside theirs. What's shared, similar, different, missing, and what each side should do about it.
studies Generate an HTML Page for Lossless and a Collaborator, Rendered in the AI Labs Splash
Step 3 of 3: turn the evidence and the comparison into one splash page. Visual highlights up top, the detailed narrative below.
augment-it Build Selector and close the keyboard contract
Nine surfaces declare a keyboard widget. Zero implement one. This is the first component whose whole substance is behaviour, so it is the first one with real tests.
augment-it Give the services a shared tsconfig base — fold ten byte-identical service configs onto a new `tsconfig.services.json`, reconcile `decile-mcp`'s real delta, fold two duplicated package configs onto the existing `tsconfig.base.json`, and correct the root fallback's stale exclude list
Ten service tsconfigs are byte-identical and extend nothing. The fix already exists one directory away — `tsconfig.base.json` did this for the apps and works.
augment-it Prove the component API end-to-end on request-reviewer — ship the scales, build Button, migrate one member, and verify by measurement
If this loop closes once it closes eighteen more times. One member, nine buttons, and a measurable accessibility delta.
augment-it Tidy every consumer onto the shared primitives
Button is done across nineteen units. This sequences what is left: Chip everywhere, the stale annotations, and the three containment jobs that are not component work at all.
augment-it Component-Level Documentation Contracts — Giving All Forty Units Their Own Four Firsts
Forty deployable units, fourteen READMEs, zero DESIGN.md files. The contract set each kind of unit owes, and the order to pay it down in.
augment-it Graphify as Standing Practice and Per-Component Diagrams — Visual Engineering That Doesn't Go Stale
The graph ran once, on 2026-08-06, and still names an app that was renamed two days later. Turning a snapshot into an instrument, and giving each unit its own picture.
augment-it Pickup notes — 2026-09-12: the watchdog got fixed, and so did the bug it was never going to catch
A "Twenty is broken" report that wasn't, a production bug that only appears on a dead socket, and three days of infrastructure that lives outside git.
augment-it Stale Corpus Sources When the Workspace Socket Is Down — the header moves, the list doesn't
Switching corpora on a dead socket silently shows another corpus's sources under the new name — a wrong answer wearing a confident label.
augment-it Back Up the Content-Ingest Corpus Volume — the corpus has no second copy
Every fetch writes to a single Railway volume that nothing backs up, nothing mirrors, and only one process can even read.
augment-it Fix Env Aliasing That Drops PUBLIC_ Vars in the Developers Menu
Assigning import.meta.env to a variable defeats rsbuild's static replacement, so two production URLs quietly resolve to localhost.
augment-it Re-Mint the Deploy-Watch Railway Token — the watchdog has been blind for days
The watchdog built so a failed deploy would not go unnoticed for twelve days has never once run green itself.
corpora-builder didi.sh Auth and Multi-Org Corpora
Log in once, hold several organizations at once, and read one federated corpus across them. Three catches, and two specs that disagree.
corpora-builder Search Index, Then Pagefind
Search reads 845 files. Phase 1 writes a manifest so it reads one. Phase 2 puts Pagefind on top of that manifest, not in place of it.
ai-labs corpora-builder on didi.sh Entities — signup, login, and who sees which corpus
The tenancy primitive is already built and it's flat. corpora-builder should inherit it, not invent a second one.
ai-labs didi.sh Login and Workspace-Delivered Config — the plan across three repos
corpora-builder should get its config — R2 credentials included — from the didi.sh workspace, not a local `.env`.
ai-labs Sync Corpora to R2, and Show Clients What Changed
The R2 prefix has held zero objects for fourteen days — and the corpus grew anyway, in git. Mirror first, version later.
flave Phase 0 — The Live Render Loop
Type Lossless Flavored Markdown, watch it become a styled document as you type, and invent new syntax without touching the renderer. The smallest thing that is already the product.
flave Phase 1 — One Operation Set, Four Callers
A menu, a palette, a rendered page you can type into, and an agent — all writing through the same named operations, so a human and an agent can never reach a state the other cannot describe.
flave Phase 2 — The Workspace and the Files Surface
Flave opens a folder, shows you what is in it, and lets you edit the theme that styles what you are reading — so design work is brought in once and reused, never recreated.
memopop-ai/memopop-orchestrator Reconciling Perplexity Citations Against Retrieved Sources
Sonar hands us the sources it actually retrieved on every call, and we throw them away — so every URL in every memo is a guess.
augment-it Test coverage — pick the harness, seed the suite from the prove-scripts, and loop the open bugs to green
Vitest + Playwright for this repo, ExUnit already standing in id-didi-sh — convert the six prove-scripts into a permanent suite, then write the humain-vc corpora bugs as failing tests and iterate until they pass.
augment-it Open augment.didi.sh to reach-edu — a second tenant instance, and Stephenie Tesoro as the first client user
The data is already deployed; only the door is single-tenant. Open it with a per-client instance, not a relaxed org check.
augment-it CRM Starter Export — the pipeline shape, enriched from the canonical layer: orgs first, then people attached
Two CSVs seed the empty CRM from the canonical layer: organizations first, people second, attached by a stable key. Corpora excluded.
augment-it Org Relations (parent/child/peer) + Org Tags — model, capabilities, and the Org Workbench surface
Organizations finally get edges to each other — parent, child, or peer, with a typed flavor and free-text human context — plus their first tag mechanism (Initiative, Program, Funder), all workable from the Org Workbench card.
augment-it Didi crawl — three targets (links, streams, team members), the relevance brief, and staged team ingest
One `organization.crawl` capability over Anthropic's server-side web_search, driven by a per-workspace, operator-editable relevance brief.
augment-it Workbench usability sweep — corpus visibility, stream editing, and promote-to-affiliation (issues #20 · #26 · #25)
Today's scope from the first real workbench session: make the person card's three invisible corpus items visible, let the operator fix a stream's kind and give it its real name, and turn a bio-page link row into a three-click affiliation.
augment-it Workspace-scope legibility — empty workspaces and stale org restores should explain themselves, not look broken
Switching to a workspace with 0 orgs made the workbench look dead — the visibility rules were right, only the messaging failed.
augment-it Augment from DB · Phase 1 — service capabilities + Exa, no UI
Four service-side deliverables that make the whole flow provable from a script before any remote exists: org detail + org affiliations reads, a registry-resolved search.fire, and Exa as a peer connector.
augment-it Augment from DB · Phase 2 — the org-workbench remote: flow registration, org search, org card
Autocomplete to a canonical org and work its card with a live ➕ on every list — plus the verb the spec missed, `organization.streams.add`.
augment-it Augment from DB · Phase 3 — the search-and-add remote: editable term, provider palette, one-click add
Launched from any 🔍 on the org card: an always-editable term bar, a provider palette, one-click add back to the launching list.
augment-it Augment from DB · Phase 4 — people reveal, person cards, add-person with automatic affiliation
The org card grows its people: every affiliated person revealed with role + relevance, nested identity links with their own ➕ and 🔍, and an inline add-person where the affiliation edge materializes without the operator ever managing it.
augment-it Augment from DB · Phase 5 — stream-scan mode: scan a pulse stream, badge the already-known, one-click the new into the corpus
Stream scan is a mode of search-and-add, not a third remote: the stream URL is the authoritative index, deduped against `content_items`.
augment-it Plan stub: ingest the next reach-edu event CSV into the canonical layer
The mechanism already exists and is proven twice over (turning-jobs, FreedomFest) — this is the sequence to run the moment the next event CSV lands, so it's 'follow the stub' instead of 're-derive the pipeline.'
augment-it Pickup notes — 2026-07-13: deploy hardening, doc audits, credential hygiene
Steps 1–10 are live at augment.didi.sh; this session cleared the production-only bugs that only using the deployed app surfaced.
ai-labs Study Agent Harnesses + Conversational UI, Then Decide the Cross-Product Native Shell
Pin two studies and audit in-house prior art before designing a Tauri shell that swaps context across three apps. No code lands here.
augment-it Build order: the humain-vc unlock flow, step by step
The execution sequence for Flow 1 — each step names its repo, files, and verification, so a fresh session can pick up mid-sequence.
augment-it Person-aware canonical resolver — closing the gap between the proven scripts and the shell-reachable capability
The resolver only knows organizations; every person and affiliation ever written came from CLI scripts no UI can reach.
augment-it SurrealDB MCP + a verification skill — querying augment-it's canonical layer directly, starting with FreedomFest 2026
ai-labs SurrealDB MCP + a verification skill — querying augment-it's canonical layer directly, starting with FreedomFest 2026
ai-labs Unlock: the humain-vc team (two people) logs into a deployed augment-it
One flow: a humain-vc member signs in with her work email, lands in her workspace, works the thesis corpus. Single-tenant deploy on purpose.
augment-it Migrate off the deprecated `nats` package to the `@nats-io/*` scoped v3 client — swap `nats@2` for `@nats-io/transport-node@3` across all 10 services, drop the removed `JSONCodec` in favor of `JSON.stringify` + `msg.json()`, and prove the inter-service bus still round-trips live before committing
`nats` → `@nats-io/transport-node` v3 across 27 files: mechanical, except the removed `JSONCodec` rewrites every encode and decode.
augment-it First-Pass Corpus Quality Scan for reach-edu — a measured before/after baseline of the RAG corpus
A read-only baseline of 517 markdown files across 57 funder dirs, taken before RAG is wired, so 'after' has a 'before' to compare to.
augment-it Canonical Entity Registry on SurrealDB Cloud — just write records
SurrealDB Cloud is up at main/main with three SCHEMALESS tables (persons, organizations, affiliations). Goal: write records from tonight's CSV+JSONL into those tables. SCHEMALESS stays. No field discipline up front.
augment-it Augmentation-state preservation and snapshot promotion — the operator's CSV is the system of record, the filesystem is the truth, and `/promote-snapshot` is the verb that walks the corpus and emits the next CSV with system columns appended so flow-switches don't erase the prior cycle's work
One verb: `/promote-snapshot` joins the corpus filesystem into a fresh CSV version with system columns. No register, no write-hooks.
augment-it Download PDFs into Corpus Inbox — preserve the original binary alongside Jina-extracted markdown; wire both inbox vectors (UI and agent-chat) so the operator's PDF discoveries land as commit-able evidence, not just summarized text
Jina gives the inbox text and throws the PDF away — nothing to cite by page or hand to a co-researcher. Save the binary alongside it.
augment-it URL Auto-Detector and Clickable Rendering for List Fields — make socials, helpful_links, and official_updates_index_urls open-in-tab links instead of opaque JSON
`socials` and its list-shaped siblings render as 12px JSON; a shape-detecting extractor makes every URL clickable and drops the clutter.
augment-it In-App Chat v0.0.1 for Augment-It — The Prompt-Drafting Triad as the Demo Affordance
Gated enhancement made conversational: `prompts.draft` → `improve` → `apply`, with postconditions that check what the prompt promised.
augment-it Shell & Micro-Frontend UX Coherence — Refactor Plan
Eight locked UX decisions sequenced into five phases — the Deck→Flow rename first, so every later phase speaks the right vocabulary.
augment-it Augment-It Workspace — Walking Skeleton Plan
Browser ↔ Workspace Service over WebSocket, Workspace Service ↔ row-store over NATS, and two real spreadsheets as the proof-of-life payload.
augment-it Impose the Three-Mode Theme System on augment-it
The two-tier tokens and light/dark/vibrant contract adapted to a federated, Tailwind-less app: one shared `packages/theme`, no raw hex.
augment-it Prompt-Template-Manager — Walking Skeleton Plan
Author `{{column}}` templates and run them per row — `prompt-runner` is the only container that calls the Anthropic API.
augment-it Run-as-First-Class-Operation — Pair Pack-Runner with Prompt-Template-Manager, Make Runs Legible Across the Pipeline
Lift `Run` from a string id buried on each response into a real entity, so any surface can see which batch produced what it's showing.
ai-labs In-App Agent Chat — Walking Skeleton Plan
One session's work: scaffold the package, do the Chroma tenant migration, and ship `slide.read` end-to-end as proof the abstractions hold.
ai-labs Agent Capabilities — Hooking the Chat Surface into Memopop
How the In-App Agent Chat pattern maps onto memopop-ai: where each layer lands in the repo, and the smallest read-only proof-of-life.
ai-labs The Anatomy of the In-App Agent Shell — Shell, Workspace, Window, Chat
"Shell" meant four things at once: layout frame, workspace package, Window, chat. The workspace is the source of truth — not the chat.
ai-labs Per-App Workspaces and the Chat as Optional Surface — The Architecture We Walked To
State of truth lives per app in `@<app>/workspace`. The chat package is UI-only, reaching it through a typed WorkspaceAdapter.
dididecks-ai Init DidiDecks as Core Submodule of AI-Labs
Carve dididecks-ai out into its own repo and re-attach it to ai-labs as a git submodule, with branch-aligned tiers.
dididecks-ai Refactor scroll-ported slides into true static play-format slides (per-client, repeat for every deck)
A reusable procedure for stripping scroll idioms — vw/vh units, reveals, marquees — from copied slides so `/play` and `/print` render them.
memopop-ai/memopop-orchestrator Migrate `studies/open-specs-and-standards/` into its own pseudo-monorepo
ai-labs Add a Chroma Local UI Interface
Local Chroma in PersistentClient mode is an embedded SQLite library with no UI of its own. Three paths to a browseable surface — from a 30-line inspect script tonight to a /chroma route in the splash later — laid out in increasing commitment.
ai-labs Context Vigilance Splash Page — Narrative Brief
Designer brief for the Context Vigilance splash. The functional plumbing exists; the structural skills are codified elsewhere. This doc is only about the *story* — the four-act narrative arc and the emotional move each act should produce.
ai-labs Track and Ingest Lossless Content into Chroma (with Change Detection)
A second ingestion pipeline parallel to the context-v corpus — for the ~5K Lossless content files scattered across the monorepo. Driven by its own sources map, with content-hash-based change detection so re-runs only re-embed what actually changed.
ai-labs Write Custom Chroma MCP Server (v0: a session-transcript ingester)
Defer djm81/chroma_mcp_server; write our own session-transcript ingester into the Chroma the corpus lives in, so the two cross-query.
prompts9
studies Kickoff: Collaborator Codebase Analysis
Act as VP of Engineering: run three subagents in sequence to compare a collaborator's agentic-coding harness with ours.
augment-it Common-Six Social Packs — First Real Packs on the Structured-Output Surface
Six pack identities — linkedin, x, bluesky, youtube, facebook, wikipedia — on one backend routing by `pack_id`, no microfrontend per pack.
augment-it Helpful Links on Records — Captured During Response-Reviewer Triage
The adjacent links a human finds while triaging die in the clipboard; `helpful_links` catches them in one click and survives derivations.
augment-it Response Reviewer — Structured-Output Extension (Packs-and-Bundles Foundation)
Build the surface every pack lands on — candidate cards, confidence pills, outcome enum — against mock fixtures. Zero packs ship here.
augment-it Run /speckit-specify — Response Reviewer Structured-Output Extension (Packs-and-Bundles Feature 1)
Feature 1 of the packs-and-bundles series: the structured-output surface every pack will land on. Zero packs, zero bundles implemented.
augment-it Build the Shell Tiling & Peek-Deck — Window the Federated Frontends
The shell stops being a tab switcher: a peek-deck at 90% width with neighbours peeking, plus a two-remote split with a draggable seam.
augment-it Run /speckit-constitution — Seed Augment-It's Constitution from Context-V
The directive to paste with /speckit-constitution so the principles synthesize from our own context-v docs, not from training data.
augment-it Run /speckit-specify — Workspace + Sidecar Foundation (Feature 001)
The workspace package and bun sidecar, plus exactly one capability — `records.import` — end to end to prove the pipe. No federation yet.
studies Create a New Study
blueprints15
augment-it Augment-It as Working App and Architecture Demonstration
Augment-it is a working product and a live architecture showcase at once; every decision answers to both lenses so neither quietly wins.
augment-it Webhook as Wake-Up, Not as Truth — relaying platform events into CI without trusting them
Polling gets throttled and push payloads are unsigned. Forward the interrupt, not the claim, and both problems stop mattering at once.
ai-labs Show the Filesystem of a Workspace
Every ai-labs app sits on a folder the user cannot see. The tree is the same five decisions each time; the backend is the only part that differs.
dididecks-ai Shared Content Modules Across Deck Surfaces
One typed content module per deck variant drives Scroll-UI, Play-UI, and the PPTX exporter — so copy cannot drift between surfaces.
ai-labs The Source Curation Gate — A Convergent Prune-and-Promote Surface for AI-Assisted Web Research
Three apps grew the same organ — a human prune-and-promote step between retrieval and generation that the writer cannot then escape.
augment-it Connecting To And Using SurrealDB
The one place that codifies how augment-it talks to SurrealDB Cloud — the five env vars, the connect → signin → use dance, the client-tagging write contract, and the dev-only-credentials posture that a proxy service eventually replaces.
ai-labs Install Auth Across Applied AI Labs Apps
Don't re-derive the auth pattern — astro-knots already shipped it. This is the ai-labs handle: what to pull in, which DB, what to translate.
augment-it Response–Row Identity Across Promote — Why Responses Outlive Their Rows, and the `record_uuid`-on-Response Fix
Promote deletes parent rows, leaving responses pointed at dead `row_id`s; carrying `record_uuid` on the response resolves them by identity.
augment-it Packs and Bundles — The Two-Tier Pattern for Entity-Profile Augmentation (and Beyond)
Two tiers: a pack is one source, one remote, one schema; a bundle is a named composition of packs fired by a single chat verb.
ai-labs Chat-As-Verb-Surface Patterns — How the In-App Chat Calls Skills, MCP Tools, and Scripts; How it Reads State and Anticipates Lightly
Five conventions that let three apps share a chat surface without sharing a package, starting with capability adapters and one envelope.
ai-labs Per-App Workspace Conventions — Discipline, Not a Shared Package
No universal `@lossless/workspace` package. What every app shares is the shape: singleton state, an activeView union, a capability registry.
augment-it Original and Enhanced Record Instances — the Record-Instance Model
No mutation, no derived set per run: one immutable original plus one mutable enhanced instance per round, promoted to seed the next.
augment-it Module Federation + Rsbuild — Dev Loop Gotchas
Five Rsbuild + Module Federation gotchas, cross-origin HMR first: none block adoption, all cost time if you don't see them coming.
augment-it Spec-Kit and Context-V Coexistence — How They Work Together in Augment-It
context-v holds the project's living memory; spec-kit drives per-feature implementation flow. Complementary, not competing.
augment-it Why Response Reviewer and Highlight Collector Exist — The Verbose-Prose-to-Tabular Bridge
CRM cells are terse and LLM answers are prose; no structured-output regime removes the human integrity check that bridges them.
reminders15
memopop-ai/memopop-orchestrator Every Step Writes Its Output To File
A run's destination folder is decided before the first step, and every step writes its result there as it finishes. Nothing lives only in memory.
memopop-ai/memopop-orchestrator Normalize Labels Gradually
One company says Total Revenue, another says Gross Revenue, a third says Top Line. One reports monthly, another quarterly, another H1/H2, another only annually. Collection never touches any of it. Normalization is a later, corpus-level act — a cluster of labels that mean the same thing, one chosen default, and an alias map — built by a person from real analysis across real portfolios, never by an agent guessing from what the words sound like.
memopop-ai/memopop-orchestrator Round-Closing Timeline Nuances
Wires arrive before and after the close they belong to, rounds close later than anyone planned, and a fund and its SPV subscribe months apart on identical terms. None of that is an anomaly. Record every date as the document states it, never revise one to make a sequence tidy, and confine anomaly-noticing to the handful of series that are actually real at this stage — money spent, web traffic, signed contracts, billed subscription revenue. Everything else is a claim or a projection, and instinctive concerns about it belong in anomalies.json rather than in the memo or the conversation.
corpora-builder The Sidecar Port Is Adopted, Not Owned
Tauri probes 8787 and uses whatever answers. A stray dev sidecar becomes the app's backend, silently, and the app looks fine.
memopop-ai/memopop-orchestrator Long-Running Is Not a Reason to Fan Out
Duration is not the variable that decides whether work should be split across agents. Continuity is. Ask before parallelizing anything whose quality depends on what came before it.
ai-labs corpora-builder Is Not augment-it Tooling
It was born inside augment-it and split out. The relationship is inheritance, not overlap — and its purpose is bigger than either app.
ai-labs Load the theme system before touching tokens
Three layers, two axes, three modes. And the ai-labs palette is augment-it's — not the shared-styles package nothing renders.
ai-labs Never Run jj in a Git LFS Repo
jj does not run smudge/clean filters. In an LFS repo it commits the real bytes over the pointers — 282 MB in one save.
id-didi-sh Dates are UTC at rest, viewer-local at render
augment-it Libraries We Do Not Use — Ever
A hard denylist of packages this codebase has removed on purpose. Do not import them, do not assume they are installed, do not re-add them.
dididecks-ai Never Use JSX Syntax
augment-it Tags Are Two Projections — Frontmatter `tags:` on Files, `has_tag` Observations in SurrealDB
Files say `tags:` because Obsidian reads files; the DB says `has_tag` because its predicates are verb-shaped. Same fact, two projections.
id-didi-sh The canonical spec lives in the ai-labs parent, not here
This repo's context-v/ holds implementation-local docs only. The spec of record — contract, session model, schema, increments — is ai-labs/context-v/specs/Id-Didi-Sh-Identity-Service.md. Read it before changing anything load-bearing.
augment-it Record Count Stays Stable Across Versions — Augmenting Adds Columns, Never Rows
One dataset, one row count, forever — augmenting adds columns, not rows. 231 rows in the store for a 96-record dataset is a symptom.
ai-labs Preferred Stack — uv over pip, and other defaults
issues62
ai-labs Splash rollup:sync fails from where the operator actually stands
`pnpm rollup:sync` errored at the ai-labs root (no such script) and inside splash/ (pnpm 12 ignored the build allowlist). Both fixed.
augment-it A component test whose fixture is simpler than its call sites
Selector--Menu's suite was green while both of its first two adopters were broken in exactly the way its header promises to prevent.
augment-it A silently ignored alias pointed a verification probe at production
rsbuild accepts source.alias and ignores it. Three agents rendered live data believing it was a fixture; one wrote a file into client corpus.
augment-it Issues raised by the migration subagent while converging request-reviewer
Findings surfaced while doing something else. Raised, not chased — the diff stays clean and the finding stays reviewable.
augment-it Structural invariants live in prose, so sweeps stop halfway and nothing notices
Three units have now been found whose typecheck had never once passed. Each was found by accident, five weeks apart, by someone tidying something else.
augment-it The federation has no layout layer, so seven of its eight deviations are about placement
The design system standardised everything that goes inside a box and nothing about the boxes. Consumers keep their freedom for now — deliberately, and on the record.
corpora-builder Need an Elegant Resolution to Source Pointers vs. Master
One source, many folders, is the design. But for 75 sources the body sits in an untriaged inbox file the scoped read never reaches.
corpora-builder 24 Orphaned bin/ Objects From a Half-Migration
A test that checked the object existed but never the pointer. Ghostscript's nondeterminism turned a sequencing mistake into 24 untraceable objects.
augment-it Every remote hardcodes the workspace WebSocket to localhost — Org Workbench loads no data on augment.didi.sh
Sixteen remotes dial `ws://localhost:3001/ws` with no env read. On prod that points at the visitor's own laptop, so the socket shows `closed` and the roster never fills.
augment-it Tokens landed, components didn't — the UI needs an overhaul, and the drift linter can't see the problem
19 of 20 apps consume the theme package; shared-ui ships exactly two components. Every remote hand-rolls its own buttons, pills, and empty states against shared colours.
flave The lfm barrel imports node builtins, so it cannot be bundled for a browser
A consumer that only wants `parseMarkdown` still drags `node:crypto`, `node:fs` and `node:path` into the bundle, because the main entry re-exports OGCache. Same class of defect lfm already documented for plantuml — but in the front door.
augment-it A failed deploy is silent, so nothing watches production after merge
Every frontend Docker build failed for twelve days unnoticed: the old container keeps serving and the health check keeps passing.
augment-it Domain type is ambient state, so a failed workspace load hides every corpus
humain-vc opened the Corpora Curator and saw 'strategy' and 'No corpora yet' — it has theses, and plenty of them. One guessed value at load time silently filtered the whole surface, and the same symptom was debugged out once already on 2026-07-07.
augment-it One stuck message kills a NATS subject until restart — `domain.list: timeout` and the sequential handler loop
Every handler in `domains.ts` consumes its subject with a `for await` loop, so one unsettled request blocks the subject until a restart.
augment-it Move the rest of the app to remote hosting — prod still falls back to localhost for every undeployed remote
12 micro-frontends are hardcoded to `http://localhost:3XXX` in the prod shell, so augment.didi.sh fetches them from the visitor's machine.
augment-it Concurrent agent searches queue into a search-results column — fire many, deal with them as they come
Agent searches run 60–210s and each one hijacks a single column. Wanted: a rightmost queue where every fired search appends its own card.
augment-it Fetch full content clobbers the operator's metadata — resets the title to a URL approximation
`fetchSourceContent` never consulted the saved title, so Jina's guess — or the raw URL on failure — overwrote what the operator typed.
augment-it Jina metadata parser is blog-only — needs two profiles + fuzzy routing (academic sources lose their date/publisher)
The parser only reads OpenGraph keys, so scholarly sources lose date and publisher to `citation_*` / `dc.*` / `prism.*` it never looks at.
augment-it No test coverage — TDD keeps getting deferred, despite being exactly the right fit for agentic development
Agents rewrite this codebase with zero automated tests — and the iterate-until-green loop is exactly what agents are best at. Pick a runner.
augment-it Parent-Child Nested Organizations Are Not Modeled — Initiatives, Funds, and Sub-Orgs Have Nowhere Canonical to Hang
`upmobility-foundation-urban-institute` welds a parent org to its initiative, so triaged content has no honest folder to land in.
augment-it Refactoring for API Speed — a single-user app should boot in milliseconds, not a minute
Measured: shell mount to workspaces ready is ~543ms. The perceived minute was a stale deploy plus remotes hanging on `localhost:3XXX`.
augment-it Search & Add's invokes never reach the workspace — the pane hangs at 'searching…' while every backend rung is green
SearXNG answers, `search.fire` answers, the org card loads — yet the 🔍 pane hangs forever. The frame dies inside the client transport.
augment-it Session expiry turns the app into a zombie — the 12h JWT dies mid-use, the UI stays up, and every invoke times out
The `didi_session` cookie lives 30 days, the JWT inside ~12h, and nothing calls `/api/session/refresh` — the transport 4401-loops at 2/sec.
augment-it Tag input swallows commas into one mega-tag — commas should split into separate tags
`toDashed` splits on every non-alphanumeric, so commas behave like spaces and three intended tags fuse into one mega-tag.
augment-it Troubleshooting workspace ↔ DB state alignment — humain-vc's corpora don't load, and the canonical layer holds fewer than the operator created
The humain-vc workspace renders empty-or-wrong corpora while the canonical layer itself holds fewer humain-vc domains than the operator remembers creating — four suspects, each with a discriminating signature.
augment-it Workspace + corpora connection is slow-to-hanging, and the auth token won't persist
The Corpora Curator sits at 'connecting…' and the workspace switcher at 'loading…' — corpora never arrive — while the didi session drops within a minute of signing in, forcing a re-login. Two symptoms that most likely share one root cause.
augment-it Funder↔strategy is tags for now — whether it deserves a real edge is deferred
140 strategy tags landed on 69 funders, but a tag can't carry evidence counts, gift sizes, or recency. The edge question comes due later.
augment-it Header polish — the FLOW label and shell suffix have outlived their jobs, and the chat toggle sits on the wrong side
Four findings from the first production walk-through — including a chat toggle on the right that opens a rail pinned to the left.
augment-it Relation kinds are inverse pairs — one stored string can't speak from both seats
NextLadder is funded_by Ballmer Group; Ballmer Group is funder_of NextLadder — the same edge needs a different kind string per perspective, and today only one pair is special-cased in a read-time map.
augment-it Capability Gaps Surfaced by the First Triage Co-Pilot Run — One Collective Ledger, Not Five Tickets
Five gaps from the first triage run — including direct SurrealDB writes whose string-typed ids silently failed to join their org rows.
augment-it Corpus adds don't fetch metadata — and the row gives no cue either way, and there's no inspector to see or fix it
`organization.corpus.add` writes url, kind, and domain then stops — the Jina metadata fetch never fires, and nothing on the row says so.
augment-it Corpus items aren't visible on person cards — and corpus coverage across entities is hard to assess anywhere
The person card says 'Corpus items 3' and shows nothing — the operator can add a fourth without ever seeing the three that exist.
augment-it Crawl progress is a black box — 'crawling the web, this takes a minute…' needs traces the operator can watch
The model narrates as it crawls — `extractText` skips straight past it to the final answer, so the operator gets a minute of ellipsis.
augment-it Crawl replies can be lost — the eternal 'crawling…' spinner (no client timeout, reconnect-dropped invokes, tight dispatch ceiling)
The Curry Foundation crawl finished in 87s and the tab spun forever: no client deadline, reconnect-dropped invokes, a 300s ceiling.
augment-it The crawl's search substrate is fixed to Anthropic web search — the operator expected to choose
The manual 🔍 has a provider palette; `organization.crawl` is hardwired to Anthropic's server-side web_search with no dial and no label.
augment-it Switching flows from the Flows popdown doesn't surface the new flow's stage — a rotation-step click is required
Switching flows flips the pill but leaves the stage blank until a step-bubble click. Only tabs with persisted layout state reproduce it.
augment-it Invokes survive reconnects — the claim protocol closes the eternal-spinner root cause
Two crawls finished server-side while the tab spun forever. Pending invokes now survive a socket drop and re-attach by id via claim frames.
augment-it List rows show hostname only — the path is hidden, so same-domain entries are indistinguishable
`AdditiveList`'s `host()` drops the pathname, so two Gates Foundation links both render as `gatesfoundation.org` and can't be told apart.
augment-it Live/not-live indicator tooling — parts of the UI feel dead, and there's no single view that says whether everything is actually working
Five distinct failures — dead remote, dead socket, dead service, no refresh, unwired button — all present to the operator as one dead click.
augment-it Merging organizations or people — when two objects turn out to be the same entity, dedupe non-destructively
Two rows are sometimes the same entity and nothing merges them — no edge re-pointing, no list union, no slug absorbed into `aliases[]`.
augment-it No component library — the UI is improvised per-remote instead of component-based, and it's starting to show
Fourteen remotes improvised their own UI, so status pills and candidate pickers now exist in parallel dialects. The bill is arriving.
augment-it No user visibility into state — the app needs a State-Inspector surface
State lives in five places and none are inspectable from inside the app — nothing shows which remote currently believes what.
augment-it Org Workbench in a narrow pane — the roster doesn't collapse, and the org card's contents spill out of their container
In a narrow pane the roster keeps its 300px and the card's link rows overflow — the flexbox `min-width: auto` trap, twice.
augment-it The Org Workbench can't create an organization — and creation must sit behind a 'be sure there is no match' gate
The workbench can only find orgs that exist. Creation must sit behind the same show-every-match gate that already governs adding a person.
augment-it A person's bio page on another org's site is an affiliation signal, not just an identity link — the UI should offer the promotion
A bio on another org's domain is three facts — identity link, affiliation evidence, observation. The card captures one and drops two.
augment-it Pulse streams need an editable kind and a user-facing name — 'Today's Credentials' is not an 'updates_index'
The operator can neither fix a stream's inferred kind nor record its name — `media_streams[]` has no title field for Today's Credentials.
augment-it The search column holds stale results — a new agent search doesn't reload it
The team crawl bypasses the Search & Add envelope, so the column sits frozen on the last search's candidates, masquerading as current.
augment-it Team-crawl accept drops the crawled links and leaves the staged row — double-save risk
`person.apply` writes `linkedin_profile_url` as a scalar only, so accept discards the crawl's links — and the staged row lingers.
ai-labs State-Inspector as a universal need — every ai-labs app hides its state from the people running it
No ai-labs app can answer "what does it currently believe?" — rune singletons, deck state, LangGraph FlowState, none inspectable.
augment-it Search Providers as First-Class — Stand Up SearXNG as the New Default for Social Packs; Tavily Stays as a Peer; Per-Row Iteration as the Workflow We're Building Toward
Tavily is a content-RAG index — wrong substrate for social-profile pages. The fix isn't a swap — it's making provider plural per-fire.
augment-it Issue: How People, Organizations, and Their Relationships Actually Enter SurrealDB
Not a bug — a verified trace of the canonical write path, because the DB already does more than the UI or the operator's memory shows.
augment-it Issue: Person · DB Resolver UI needs to accommodate multiple organizations per person
`person-db-resolver` resolves one org per row, but Lincoln Ellis's bio names four — no way to add an Nth without re-running the row.
ai-labs The Drag in AI-Assisted Web Research — Diagnosis, Prior Art, and the Open Forks for a Source Curation Gate
AI research yields enough hallucinated sources that manual Google + Docs looks time-competitive. The drag is structural, not a prompt bug.
augment-it Grilling on the DB Resolver — questions to settle before v0.0.0.2 / v0.0.0.3
Three decisions before v0.0.0.2: where the join key lives, whether a slug can be renamed safely, and whether opportunities reopens Decile.
augment-it Personal-link observations need named query lenses — without them, an accumulating fact log goes uninspected
`has_personal_link` observations carry rich qualifiers and no queries. One thought leader can contribute 50+ before anyone can look.
augment-it Some records show empty corpus in the Sort & Filter Lens despite per-funder directories existing on disk — the lineage join is healthy but the workspace-service capability has no timeout override (defaults to 5000ms), the content-ingest handler processes requests serially, and each call walks every funder directory under clients/<id>/corpus/, so late requests in the 96-row fan-out time out and the lens swallows the error silently; the durable fix is to make corpus_funder_slug (a column the records sheet already populates) the primary join key, which limits each call to one small directory and dissolves the timeout race — this supersedes the originally-proposed corpus-overrides.yaml because the override surface is now the records-sheet cell
No `CAPABILITY_TIMEOUTS_MS` entry for `corpus.list_for_record` — 96 parallel calls hit the 5000ms default and the lens swallows the error.
augment-it Funder Corpus First Session Failed — 75 markdown files across 15 of 96 funders, 81 records unprocessable, hours spent layering filters on stale data instead of producing clean fresh data, rebuild against the goals spec exists in code but was never validated against a real pack fire because the session ended
Six hours produced 75 corpus files across 15 of 96 funders — 81 records still have nothing. This is the failure-mode list for morning-self.
augment-it OfficialPulse URLs Appear as Junk in Promoted Versions — operator believes promote v6 → v7 → v8 wrote bad data into the array column; audit shows promote is clean and v6 itself already contained every URL
Promote added nothing — v5 through v8 carry identical 122-URL arrays. The new renderer just made them visible, and no UI can remove one.
augment-it Augment Transformations Not Reliably Persisting — Hand-Curated Field Edits and Whole-Row Augmentations Are Disappearing Across Record-Set Versions
98 hand-curated URLs across 45 records with no save or promote affordance — only the row-store's auto-persisted JSON keeps them alive.
augment-it Troubleshooting UI for Official Blogs — The Bundle Fire Path Doesn't Fit the Flow That Was Built for Prompt Templates
Bundles fire end-to-end, but the Flow assumes every fire routes through a prompt template — so every step past 2 is wrong for a bundle.
augment-it Changelog entries duplicated across augment-it/changelog/ and content/changelog--laerdal/
Eleven backfilled augment-it changelog entries currently live in two places. Either location can be the source of truth — but right now both are, and updates have to be made twice.
context-vigilance-kit context-vigilance-kit/issues/index
issue-resolution2
memopop-ai/memopop-orchestrator Research Agent Concatenates Multiple Sources Under One Citation ID — And No Validator Catches It
`research_enhanced.py` writes several sources onto one `[^N]:` line, so downstream parsers keep the first and silently drop the rest.
memopop-ai/memopop-orchestrator Section Citations Orphaned When Definitions Live in 1-research/
`consolidate_citations.py` reads `### Citations` only inside section files, so defs living in `1-research/` become orphans.
sitemap29
dididecks-ai /data-assets/slides — reviewer audit of the slide tier, one row per slot, adapted-vs-stub per variant
The third data-assets audit and the only one never promoted to the shell — adapted-vs-stub per variant, living only in calmstorm-decks.
dididecks-ai DeckFrame--Play-UI — Play-UI chrome wrapper around SlideCanvas, plus the keyboard contract
Play-UI's outer frame at `/play/[deck]/[variant]/[slot]/` — `<SlideCanvas>` plus the floating DeckChrome and document keyboard listener.
dididecks-ai DeckMatrix — the rich audit-rated dual-surface matrix; the deck-level review surface, embeddable on any landing
The embeddable variants × slots matrix: each cell pairs a Scroll-UI and Play-UI rating, with `≠` flagging where the two surfaces disagree.
dididecks-ai DeckStatsPanel — the 4-tile quick-stats row above the matrix on landing pages (Variants · Slide Files · People · Companies)
Four-tile stats row above `DeckMatrix` — Variants, Slide Files, People, Companies — counted from the same globs `/data-assets/*` uses.
dididecks-ai ModeToggle — three-mode color-toggle (light → dark → vibrant) with per-client localStorage namespace
Fixed top-right button cycling light → dark → vibrant, persisted under a per-client `{client}:mode` key so co-hosted decks don't collide.
dididecks-ai PageAsDeckWrapper — Scroll-UI navigation primitive: scroll-snap + keyboard + section counter + reveal-on-intersect
Wraps `<section data-slot data-variant>` children in a scroll-snap deck: keyboard contract, section counter, and `#s-N` hash nav.
dididecks-ai PlayChrome — DEPRECATED thin shim around DeckChrome
Deprecated as of v0.2 — a thin shim around `<DeckChrome>` kept so external imports keep working. Removed in v0.3.
dididecks-ai ScrollDeckPage — THE single shell overlay for a scroll-deck variant page; one-import wiring
Collapses the three shell imports a variant page used to need — pagination, rating pill, mode toggle — into one component and mount site.
dididecks-ai SlideShell — shared per-slide chrome (padding, min-height, snap-align, optional consumer-provided mark)
Outer `<section>` with shared per-slide layout plus a `<slot name="mark">` — consumers plug their own mark, the shell stays brand-agnostic.
dididecks-ai lib/deck-overview — registry + filesystem walker; loadDeckOverview(deckSlug) returns DeckOverview with variants/slots/per-slide-file flags
`loadDeckOverview(deckSlug)` reads registry paths off `globalThis.__dididecksShellOptions`, so the shell never needs the consumer's imports.
dididecks-ai Sitemap — Living Map of the DidiDecks Universal-Frontend-over-Client-Decks Architecture
One mini-spec per `@dididecks/shell` artifact — the universal layer; per-client overrides live in each client-site's own `context-v/`.
dididecks-ai /data-assets/companies — reviewer audit of portfolio-company metadata + brand assets across every engagement layout
Reviewer audit over `data/**/portfolio/*.md` — companies are told from people by the *absence* of `role_class`. SSR'd behind auth.
dididecks-ai /data-assets/people — reviewer audit of team / advisor / portco-ceo metadata + headshots across every engagement layout
Reviewer audit over `data/**/{team,portfolio}/*.md` — people are told from companies by the *presence* of `role_class`. SSR'd behind auth.
dididecks-ai /play/[deckSlug]/[variantSlug]/print/ — one-shot PDF export surface; renders the whole variant stacked for the browser print dialog
Stacks every slot as SlideCanvas instances with `page-break-after: always`; no `@page` override, so the browser picks paper size.
dididecks-ai /toc/[deckSlug]/ — deck-level dual-surface review matrix (one row per slot × one column per variant)
The deck-level review matrix: variants × slots with dual-surface ratings per cell, distinct from the per-variant `/toc/[deck]/[variant]/`.
dididecks-ai runtime/mode-switcher — TS factory createModeSwitcher({client, defaultMode, respectSystemPreference}); per-client localStorage namespace
Three-mode state machine factory, namespaced to `{client}:mode` in localStorage and installed as a `window.modeSwitcher` singleton.
dididecks-ai /dev/icons — recurring design-review workbench
A kept design-review workbench — one `/dev/*` page rendering every candidate for a visual-primitive decision side by side, in real context.
dididecks-ai DeckChrome — themable floating navigation capsule for Play-UI (and eventually Scroll-UI variant cycling)
Floating bottom-right nav capsule replacing v0.1's dark PlayChrome bar; styling comes only from `--ddd-chrome-*` custom properties.
dididecks-ai DeckOverlay--Play-UI — the floating overlay layer for Play-mode decks
Single mount point on the play-slot route composing DeckChrome and SlideRankPill; its `<section data-slot>` wrap is the play-mode adapter.
dididecks-ai DeckOverlay--Scroll-UI — the floating overlay layer for Scroll-mode decks
Layout-neutral (`display: contents`) mount for the affordances riding over a scroll deck — each a named slot consumers can rearrange.
dididecks-ai DecomposeFirstPlaceholder — empty-slot fallback rendered when a per-slide file doesn't exist yet
Empty-slot fallback on the play route — an invitation to begin the rank → decompose → recreate loop, deliberately not an error state.
dididecks-ai DididecksNav — shell-injected global header linking Scroll · TOC · Play · Changelog
Shell-injected global header auto-mounted on `/toc/*` and `/play/*`, with links derived from the consumer's own deck registry.
dididecks-ai SlideCanvas — pure-CSS 16:9 wrapper that scales a 1920×1080 stage to fit any canvas
Pure-CSS 16:9 stage — container queries scale a 1920×1080 design size to any canvas, so the Play-UI scaling pipeline needs no JS.
dididecks-ai SlideRankPill — floating five-button classifier for the active slot (rename pending → SlideClassifierPill)
Bottom-right floating pill exposing the five-state classifier for the active slot, found via IntersectionObserver over `section[data-slot]`.
dididecks-ai /api/slide-decompose — non-destructive stub generator for the Phase 1 → Phase 2 transition
Dev-only route that writes an empty per-slide stub and refuses to overwrite — 409 if the file exists. Static Vercel builds never carry it.
dididecks-ai /api/slide-rank — read + write per-slide classifier state into the consumer's audits file
Dev-only GET/POST over `data/audits/slides.json` — `'pending'` is never persisted; posting it deletes the entry. 404s in production builds.
dididecks-ai /play/[deckSlug]/[variantSlug]/ — variant-index redirect to slot 01
Enumerates every (deck, variant) and 302s to slot 01 — unconditionally today, so slot-less variants like chroma's proto land on a 404.
dididecks-ai /play/[deckSlug]/[variantSlug]/[slot]/ — single-slot Play-UI renderer with keyboard nav
Static per-slot route: dynamic-imports `slides/{variant}/{slot}-{slug}.astro` into SlideCanvas, falling back to DecomposeFirstPlaceholder.
dididecks-ai /toc/[deckSlug]/[variantSlug]/ — bird's-eye-view audit dashboard with rank pills + scaffold buttons
Per-variant TOC — one row per slot with five rank pills and a scaffold button POSTing to `/api/slide-decompose`. Read-write in dev only.
context-v203
context-vigilance-kit Context-V Is an OKF Profile
Any tool that reads Open Knowledge Format can read a context-v folder. The price is one frontmatter field and an index file.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Agent-Native
The chat isn't bolted onto the app. The app's operations are one action registry that the UI, the agent, MCP, A2A and the CLI all call, and the conversation is just one more caller.
flave Handoff — the delta to MVP, 2026-10-03
Read this first if you're picking up flave. The editor works. The part that is the product, one document published to several audiences with proof nothing leaked, has no code yet. Here is that work, in order, with the decisions that gate it.
augment-it Adopt Selector in one member
The test comes before the refactor. This is the first organ whose defects are invisible — a broken keyboard renders perfectly.
augment-it The list-surface paradigm — CardRow, ListContainer, and where selection lives
Sixteen of eighteen members are the same shape: controls up top, a generated list below. Five decisions are open; the BEM rollup makes most of them reversible.
augment-it Adopt CardRow and a SelectWrapper in one member
The pilot executor. Three members answer the open decisions with evidence; everything mechanical is inherited from the Button loop.
augment-it Adopt the shared Button in one member — the per-member executor for the Button rollout
One member per run, never a sweep. Replace the buttons, delete the recipes they made redundant, raise everything else.
augment-it Adopt the shared Chip in one member
The per-member executor for the Chip rollout. Inherits every probe and verification rule from the Button loop; what differs is the judgement about what a chip even is.
augment-it Converge the federated design system — scan members for organs, fingerprint them, and triage divergence into five verdicts
Creativity is the default and stays the default. The loop's job is to notice when two teams solved the same problem twice without meaning to.
augment-it Setting up a micro-frontend with the monorepo configurations it actually needs
Three live remotes shipped without a registry row and were invisible to every check for months. This is the list that prevents the next one.
augment-it The federal layer never shipped --space-*, --radius-* or --z-* — so ten members invented token names and let the fallback carry the value
170 declarations across the federation reference tokens that do not exist. Each one silently ships its literal in all three modes.
augment-it sort-filter-lens leaks 61 unnamespaced classes into every other remote — and .error, .row and .muted are live collisions today
One member ships 511 lines of global CSS with no root-class containment. Sixteen other surfaces render a class it restyles.
augment-it Two palette steps share one hex, so dark-mode borders measure 1.00:1
graphite-700 and graphite-800 are both #232634. Four federal boundary findings came out of one member's probe; three survive adjudication and one does not.
augment-it Endow a Component With Its Own Contracts
The repeatable procedure for giving one unit — service, remote, package, or shell — the four firsts it owes. One unit per run, never a sweep.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Automerge
The only entry where two people editing the same paragraph is a solved case rather than a second file with a longer name — and it costs you the filesystem.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Git-Annex
Content is optional. git tracks which copies exist where, and refuses to drop the last one — the bookkeeping that makes deleting a local file safe.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Jujutsu
The storage layer is five pluggable backends, not one — and only two of the five have a shipped implementation you could put in a bucket.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Kopia
Its snapshot manifest has the free-text Description field restic lacks, and its policies attach per directory and inherit — the ask's own shape, in the store.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Rclone-UI
The only entry that solves the trigger problem — 5,167 lines of Rust registering jobs with launchd, crontab, and Task Scheduler behind one trait.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Restic
Its on-disk layout is data/<ab>/<sha256> plus snapshots/<id> — which is corpora-builder's unbuilt Phase 4, already shipped and hardened since 2014.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Seafile
Git's object model with content-defined chunking underneath and a human-readable description on every commit — and the S3 backend is the paid tier.
studies/sync-and-content-version-control studies/sync-and-content-version-control/profiles/Profile__Syncthing
Closes a question two Lossless docs left open: a receive-only device does not silently orphan the collaborator's edit — it flags it, counts it, and offers Revert.
flave Ideas — the editor surface and the format
Fifteen ideas captured from a working session, sorted by what they would actually cost. Four are nearly free because the groundwork already shipped; two need work upstream in lfm before flave can touch them; one is already an open decision in the spec under a different name.
augment-it Rename the corpora curator — finishing a rename that only ever reached the label
Four naming layers were tangled here and only three moved — the fourth is a data value living in two external client repos.
corpora-builder Autonomy Gates — what an agent may do here unattended, and where it must stop
A written answer to "may I proceed?" — a green list that needs no permission, a red list that always does, and the four gates in between.
corpora-builder Spec to Shipped with TDD — the two-role loop that runs unattended
A two-role loop — PM enumerates the tests, engineer implements to green — with status derived by running the suite, never asserted in prose.
augment-it Sharing code without breaking microfrontend autonomy: build-time import IS the copy
With no `shared` block, a workspace import is inlined into all seventeen bundles. The cost isn't runtime coupling, it's redeploy fan-out.
augment-it Why this monorepo does not need Turbo: a task graph with no edges
Turbo's core directive is `dependsOn: ["^build"]` — build my dependencies first. No package in packages/ has a build step, so it resolves to nothing. We adopted a best practice for an architecture we then didn't build.
augment-it Structural refactors surfaced by the codebase graph — the deadweight, the boilerplate, and the CSS convergence problem
A zero-token graph over 490 files found ~500 lines that delete cleanly, 11 near-identical `mount.ts` files, and no duplicate CSS after all.
augment-it From a Raised Issue to Fixed-and-Shipped — the bug-to-ship loop
A raised issue becomes a context-v issue doc, a gh issue, then an attempt→verify cycle that safety-commits every failed try and milestone-commits the win — closing with a changelog beat and an offer to bump semver + tag.
augment-it Sweep — Local & Federated Design System for Fidelity
The repeatable procedure for checking a member's CSS against the federal contract. The one sanctioned exception to the two-file rule.
augment-it The four layers: pnpm, Turbo, rsbuild Module Federation, and where Bun would fit
There isn't one 'monorepo' system — there are four independent ones, and the word 'federation' means two different things across them. Untangling which tool owns which job, and what Bun would actually replace.
augment-it Two tiers: WebSocket to the gateway, NATS between services
The browser talks WebSocket to one gateway; the gateway talks NATS to every service. They aren't alternatives — they're two legs of one design, and the gateway between them is where tenancy lives.
augment-it Implement-Feature Loop — plan → gh tickets → code/verify/changelog/commit per ticket → human browser test → ship
The generic feature-execution cadence: a signed-off plan becomes gh tickets, each ticket lands as verified code + a changelog beat + a conventions-clean commit, and the run closes with a human browser test and a ship() commit.
augment-it Loop through a spec — write the plan, implement, test, changelog, commit, repeat until Shipped
The phase loop that took Augment-From-DB-Flow from Signed-Off to Shipped in one day: plan, implement, prove, changelog, commit — per phase.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Paxm
Paxm is not a memory store — it is routing and durability in front of seven-plus pluggable backends, and it does zero semantic dedup.
studies/agent-harnesses Agent Harnesses — Answers to the Plan's Targeted Questions
Phase 2, not a survey: three questions — MCP tool scoping, trajectory logs, per-project config swaps — answered from the profiles.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Aider
Aider has no tool-call loop and no MCP client — not a thin one, none at all. It reads diffs straight out of plain chat text.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__AutoGen
Every AutoGen team type overrides exactly one method — `select_speaker()` — and that single seam is the whole difference between them.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Cline
"Memory Bank", the cross-session memory pattern Cline is best known for, has zero lines of code behind it.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Codex
Codex compiles a real Apple Seatbelt profile and Landlock ruleset: a fully autonomous session that never prompts is still jailed by the OS.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Continue
Five differently-scoped assistants can ship side by side in one project and swap mid-session — hot-swapping a skillset per project.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Goose
In Goose, "extension" just means "a live MCP client" — and two variants skip the subprocess entirely to run in-process.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__MCP-Python-SDK
The pinned checkout is the unstable half of a rework: v2 swaps `FastMCP`/`ClientSession` out for `MCPServer`/`Client`.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Opencode
A terminal coding agent with 38 SQLite migrations and real OTLP tracing — built like a production SaaS backend, and no Go anywhere.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__OpenHands
Pin `OpenHands/OpenHands` today and you do not get the agent — the CodeAct loop moved out to a versioned pip dependency.
studies/agent-harnesses studies/agent-harnesses/profiles/Profile__Pi
Pi's docs refuse MCP, sub-agents, permission popups, and plan mode by name — then ship every one as a first-party example extension.
studies/conversational-ui-and-native-shells Conversational UI / Native Shells — Answers to the Plan's Targeted Questions
Phase 2, not a survey: two questions — Dive's Electron/Tauri migration and anything-llm's workspace switch — answered from the profiles.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__5ire
5ire's MCP layer has no apply button — editing a server row in PGlite makes the client reconnect via the live-query changefeed.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Anything-LLM
A "workspace" is a config row over one always-shared backend: the chat provider varies per workspace, the vector DB never can.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Dive
Two native shells, neither containing a line of agent logic — both are thin supervisors spawning the same Python subprocess.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Kaas
Every credential, provider quirk, and even context assembly lives in Rust; React gets typed `invoke()` calls and nothing else.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Open-Vibe
One real OS child process per workspace — but only ever one binary. What varies per workspace is the invocation, not the backend.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Openagent
Delegation recursion is prevented not by a depth counter but by never registering `spawn_agent` on the child's tool server.
studies/conversational-ui-and-native-shells studies/conversational-ui-and-native-shells/profiles/Profile__Routa
The swappable unit turns out to be the session, not the workspace: two sessions in one workspace can run two different agent CLIs.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Understand-Anything
When an LLM authors your graph, the schema layer stops being a validator and becomes a repair shop — alias maps fold synonyms back.
dididecks-ai Loops — recurring maintenance disciplines that keep the repo legible over time
A new context-v category for skills that aren't one-shot specs or plans but **recurring rhythms** — the small, regular maintenance moves that keep a fast-moving repo readable to humans + agents who weren't there when the work happened. Each loop lives as its own subdirectory with a SKILL.md, optional scripts/, and templates/. Companion concept (TBD): `context-v/pairing/` for human-agent collaboration disciplines.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Beads
Not one embedding anywhere in the recall path — retrieval is a SQL view and a graph walk over the agent's own work graph.
studies/vector-databases studies/vector-databases/profiles/Profile__Chroma
The hybrid retrieval in Chroma's docs raises `NotImplementedError` on a laptop — `Collection.search()` is gated behind Cloud.
studies/vector-databases studies/vector-databases/profiles/Profile__LanceDB
The database *is* the file format: a `.lance` directory DuckDB, Polars, and Pandas read with no LanceDB process running.
studies/vector-databases studies/vector-databases/profiles/Profile__Milvus
One Milvus deployment is not a process — it is nine roles, three external dependencies, and a C++ ANN core reached through cgo.
studies/vector-databases studies/vector-databases/profiles/Profile__pgvector
About 3k lines of substantive C, and it inherits MVCC, WAL, replication, PITR, and row-level security completely untouched.
studies/vector-databases studies/vector-databases/profiles/Profile__Qdrant
Qdrant estimates a filter's cardinality *before* searching, which is why recall doesn't collapse the moment you filter on `tenant_id`.
studies/vector-databases studies/vector-databases/profiles/Profile__Weaviate
The database itself calls OpenAI to embed on write and Cohere to rerank on read — the RAG pipeline lives inside the store, not the app.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__ByteRover
The memory store is a directory of Markdown you can cat, grep, and diff, with its own git history. Recall is BM25, not embeddings.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Hindsight
`fact_type` is a database CHECK constraint: world facts and first-person experiences travel through different extraction prompts.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Honcho
Collections are unique on (observer, observed, workspace) — Honcho indexes memory by relationship rather than by user.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__OpenViking
Memories, resources, and skills collapse into one `viking://` tree, and retrieval is a recursive directory walk, not a vector query.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__RetainDB
Supersession as an actual indexed column — `validUntil`, `supersededBy` — rather than something the ranker is hoped to handle.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Supermemory
The most polished client surface in the study, wrapped around an engine that is not in the repo — every SDK points at a hosted API.
augment-it context-v for augment-it
Living documentation for augment-it — specs, habits, prompts, reminders, explorations, issues.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Graphify
The whole memory layer is one in-process NetworkX graph and a `graph.json` you can copy around — no database anywhere.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Delta-Mem
Memory as a dense rank-8 state matrix inside each attention head, updated token by token — the model never looks anything up.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Graphiti
`expired_at` is when the engine retired a fact; `invalid_at` is when it stopped being true in the world. Routinely different dates.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Letta
The one entry where the agent itself — not an extraction pipeline, not a background summarizer — is the memory manager.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Mem0
Despite the graph-memory marketing, the graph is an array of linked memory IDs hanging off spaCy-extracted entities.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__MemPalace
The counter-bet: extract nothing. Raw 800-character chunks score 96.6% R@5 on LongMemEval at zero LLM calls.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Neo
Familiar high-confidence queries get dialled down to low reasoning effort — memory shows up as a smaller bill, not better accuracy.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__StateBench
The trade nobody advertises: more context raises decision accuracy and superseded-fact resurrection together.
studies/memory-layers-for-agents studies/memory-layers-for-agents/profiles/Profile__Volt
Numeric thresholds decide when to compact, and the model is only ever asked to write summaries. Long-horizon coding as a DB problem.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__Superpowers
A SessionStart hook injects the bootstrap skill as `<EXTREMELY_IMPORTANT>` before the agent has written its first word.
memopop-ai MemoPop AI — Ideogram OG Image Brief
A house-style Ideogram prefix and suffix any scene description plugs into, so splash, changelog, and context-v imagery stay one family.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__OpenUI
JSON spends ~30% of its bytes on punctuation an LLM has no reason to emit; the same seven UIs cost 47–67% fewer tokens in OpenUI Lang.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__12-Factor-Agents
Nothing to install — thirteen essays whose answer to "who owns the prompts, the context, the state, the control flow?" is always *you*.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__Agent-2-Agent
The load-bearing commitment isn't the JSON-RPC — it's *opacity*. An A2A agent publishes skills, never its prompts, memory, or tools.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__AGENTS-md
The entire specification is one precedence rule: the closest `AGENTS.md` to the edited file wins. No schema, no validator.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__GSD
GSD's wager is that the limiting factor is context rot, not spec rigor — so it ships no spec grammar and resets the window per task.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__llms-txt
The only behavioral semantic in the whole format is an H2 named `## Optional` — links there may be dropped when context is tight.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__MCP-API
However many APIs a user registers, the model only ever sees two tools: `ListAvailableApis` and `CallApi`.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__Model-Context-Protocol
The three *client* primitives — Sampling, Roots, Elicitation — let a server use the host's model without ever getting the user's key.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__Symphony
OpenAI shipped the spec, not the product: 2169 lines of RFC 2119 with sections *deliberately made redundant* for coding agents.
dididecks-ai Implementation Notes for Deck Iteration Workflow
dididecks-ai Phase Implementation Template
dididecks-ai Slide Variant Template
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__Frictionless-Specs
This one specs *datasets*: every RFC 2119 "MUST" in the prose maps onto a constraint in a published JSON-Schema profile.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__OpenSpec
An LLM should never re-emit a whole spec to change one line, so changes ship as `ADDED` / `MODIFIED` / `REMOVED` deltas.
studies/open-specs-and-standards studies/open-specs-and-standards/profiles/Profile__Spec-Kit
No plan gets past the Simplicity, Anti-Abstraction, and Integration-First gates without a written, paper-trailed exception.
studies Create Study Everything as Code
memopop-ai/memopop-orchestrator Introducing a Content Density Mode System
A system-level content mode toggle (redundant vs concise) that alters the behavior of the writer, table generator, and quality agents to match different firm preferences for information density and repetition.
memopop-ai Preferred Format for Changelog
memopop-ai/memopop-orchestrator Multi-Agent Orchestration for Investment Memo Generation
An exploration into using AI supervisors and specialized agents to generate high-quality content and documents.
memopop-ai/memopop-orchestrator Portfolio Listing Agent and Current Portfolio Section
Design notes for the portfolio_listing_agent that builds a Current Portfolio subsection and structured JSON for LP-commit emerging manager fund memos.
augment-it augment-it/agent-skills/decile-hub-interface/SKILL
augment-it augment-it/agent-skills/inbox-curation/SKILL
augment-it augment-it/agent-skills/triage-inbox-w-suggestions/SKILL
context-vigilance-kit context-vigilance-kit/decisions/index
context-vigilance-kit context-vigilance-kit/index
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/ecosystem
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/philosophy
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/playbooks/github-pages-deploy
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/playbooks/llms-txt-and-md-sidecars
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/playbooks/new-site-setup
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/playbooks/opengraph-system
dididecks-ai dididecks-ai/agent-skills/astro-knots/references/tech-stack
dididecks-ai dididecks-ai/agent-skills/astro-knots/SKILL
dididecks-ai dididecks-ai/agent-skills/changelog-conventions/references/changelog-first-development
dididecks-ai dididecks-ai/agent-skills/changelog-conventions/references/filename-conventions
dididecks-ai dididecks-ai/agent-skills/changelog-conventions/references/frontmatter-spec
dididecks-ai dididecks-ai/agent-skills/changelog-conventions/references/voice-and-shape
dididecks-ai dididecks-ai/agent-skills/changelog-conventions/references/what-counts
dididecks-ai dididecks-ai/agent-skills/changelog-conventions/SKILL
dididecks-ai Title in title case
One-sentence hook that makes the reader want to keep reading. Specific, not generic.
dididecks-ai PRODUCT vX.Y.Z — Release Title
What this release does in one attention-grabbing sentence
dididecks-ai dididecks-ai/agent-skills/context-vigilance/references/developing-a-spec
dididecks-ai dididecks-ai/agent-skills/context-vigilance/references/doc-type-guide
dididecks-ai dididecks-ai/agent-skills/context-vigilance/references/frontmatter-spec
dididecks-ai dididecks-ai/agent-skills/context-vigilance/references/philosophy
dididecks-ai dididecks-ai/agent-skills/context-vigilance/references/status-discipline
dididecks-ai dididecks-ai/agent-skills/context-vigilance/references/versioning
dididecks-ai dididecks-ai/agent-skills/context-vigilance/SKILL
dididecks-ai Blueprint: TITLE HERE
dididecks-ai TITLE HERE
dididecks-ai Issue: TITLE HERE
dididecks-ai Prompt: TITLE HERE
dididecks-ai Reminder: TITLE HERE
dididecks-ai TITLE HERE
One sentence that makes a reader want to keep reading. Newsroom-style hook — not a description.
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/15f60674bf070c2f
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/25f0de5c86750b7e
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/38b666f4189ea895
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/40f956e078923920
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/6c019018c31645a0
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/76082587295e27c1
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/795e94c1c0c2cc5a
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/88d0ded5729b5482
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/a2c70d73d66ca2cc
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/b1a9507c907e5868
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/ba5de0bff3839e6d
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/c4c0fa68d0682b61
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/e552f2b87caf8f63
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/f57055e06641af3c
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/cache/calm-storm-ventures/jina/fa616c0558874713
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/examples/example-firm
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/future-work
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/routines/investor-credibility-ingest
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/routines/triage-brand-assets
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/schema/company
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/schema/firm
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/schema/person
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/setup
dididecks-ai dididecks-ai/agent-skills/crawl-fetch-ingest/SKILL
dididecks-ai dididecks-ai/agent-skills/deck-iteration-workflow/SKILL
dididecks-ai dididecks-ai/agent-skills/generate-consistent-og-images/SKILL
dididecks-ai dididecks-ai/agent-skills/loops/git-conventions/references/body-structure
dididecks-ai dididecks-ai/agent-skills/loops/git-conventions/references/examples
dididecks-ai dididecks-ai/agent-skills/loops/git-conventions/references/header-patterns
dididecks-ai dididecks-ai/agent-skills/loops/git-conventions/SKILL
dididecks-ai dididecks-ai/agent-skills/loops/maintain-design-md/SKILL
dididecks-ai dididecks-ai/agent-skills/loops/maintain-design-md/templates/design-md-scaffold
dididecks-ai dididecks-ai/agent-skills/loops/maintain-filemap/SKILL
dididecks-ai dididecks-ai/agent-skills/lossless-flavored-markdown/references/extensibility
dididecks-ai dididecks-ai/agent-skills/lossless-flavored-markdown/references/frontmatter-schema
dididecks-ai dididecks-ai/agent-skills/lossless-flavored-markdown/references/package-and-setup
dididecks-ai dididecks-ai/agent-skills/lossless-flavored-markdown/references/syntax-and-directives
dididecks-ai dididecks-ai/agent-skills/lossless-flavored-markdown/references/triggers-to-component-pipeline
dididecks-ai dididecks-ai/agent-skills/lossless-flavored-markdown/SKILL
dididecks-ai dididecks-ai/agent-skills/maintain-splash-pages/SKILL
dididecks-ai dididecks-ai/agent-skills/open-graph-share-seo-geo/references/llms-txt-implementation
dididecks-ai dididecks-ai/agent-skills/open-graph-share-seo-geo/references/seo-best-practices
dididecks-ai dididecks-ai/agent-skills/open-graph-share-seo-geo/references/sitemap-implementation
dididecks-ai dididecks-ai/agent-skills/open-graph-share-seo-geo/references/unfurler-matrix
dididecks-ai dididecks-ai/agent-skills/open-graph-share-seo-geo/references/user-tools-for-image-generation
dididecks-ai dididecks-ai/agent-skills/open-graph-share-seo-geo/SKILL
dididecks-ai dididecks-ai/agent-skills/overlay-svg-text/SKILL
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/references/anatomy
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/references/branch-alignment
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/references/content-rollup
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/references/lifecycle-workflow
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/references/search-first
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/references/the-tree
dididecks-ai dididecks-ai/agent-skills/pseudomonorepos/SKILL
dididecks-ai dididecks-ai/agent-skills/README
dididecks-ai dididecks-ai/agent-skills/remake-deck/SKILL
dididecks-ai dididecks-ai/agent-skills/search-lossless-corpus/SKILL
dididecks-ai dididecks-ai/agent-skills/setup-new-dddecks-workspace/SKILL
dididecks-ai dididecks-ai/agent-skills/slide-target/SKILL
dididecks-ai dididecks-ai/agent-skills/study-repos-first/SKILL
dididecks-ai dididecks-ai/agent-skills/theme-system/references/file-organization
dididecks-ai dididecks-ai/agent-skills/theme-system/references/two-tier-tokens
dididecks-ai dididecks-ai/agent-skills/theme-system/references/vibrant-mode-implementation
dididecks-ai dididecks-ai/agent-skills/theme-system/SKILL
hope-ai hope-ai/agent-skills/personal-strategic-plan/SKILL
memopop-ai/memopop-orchestrator memopop-ai/memopop-orchestrator/agent-skills/setup-new-firm/SKILL
studies Study Kickoff — Content Authoring Tools