Kinds / Canonical
specs/
What is being built and why. Living documents, revised as the work changes.
140 files · 23 projects
augment-itai-labs37
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.
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.
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.
Federated Component Libraries
One gallery runtime, seventeen sovereign catalogs — every member publishes what it is made of, at its own address.
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.
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.
Design System Portal
Specification for the portal that renders the federated design system — the swatch page, the token catalogue, the member index.
Federated Design System Architecture
The organising specification for augment-it's two-tier, seventeen-member design system.
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.
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.
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.
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.
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.
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.
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.
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.
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 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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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=`.
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.
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.
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.
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 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.
augment-it/specs
Open Call Specs17
Churn: An AI content editor for the Internet has been missing.
Content Management Systems are an old paradigm, they are clunky, they are rarely where creatives develop content. HTML and CSS need to marry Content Editors
Markdown-Serve: `md-serve` - a simple server and API for Markdown content rendering on the web
Markdown files have been the lingua franca of web content, on the rise since JAM Stack adoption. Yet, the development experience requires long builds, complex setups, massive content filling developer projects. Why not improve developer experience while making it easier to serve and render them?
AI-Powered Link Aggregator for Product Digital Footprint Discovery
Automatically discover and catalog social media profiles, code repositories, blog feeds, and other digital presence links for 1,400+ products in our tooling directory.
An Obsidian Plugin that uses AI to Browserless Search, Perplexity API, follows outline
Extend Perplexed to summarize products
YAML Frontmatter Error Detection and Correction System
Let content teams develop content. Handle frontmatter inconsistencies gracefully for a seamless user experience.
Project Routing Collision Fix
Cleaned route collisions between Client Projects and canonical Projects, yet now need to figure out Client Projects again.
AI-Powered Link Aggregator for Product Digital Footprint Discovery
Automatically discover and catalog social media profiles, code repositories, blog feeds, and other digital presence links for 1,400+ products in our tooling directory.
A Collaborative Markdown-based Desktop Publisher
Technical specification document outlining implementation details
Dynamic Webpage to Display Portfolio w Authentication
Dynamically display portfolio information on a branded webpage, with certain types of information only displayed for certain privileges connected to authentication.
Self-Updating Product Announcement Watcher
Automatically monitor, collect, and catalog product releases and announcements for 1,400+ tools in our content library without manual intervention.
Complete Me: A context-aware, blazing fast markup editor.
Streamlines data entry and development workflows through rigorous, context-aware autocomplete in markup and json.
Build-Out-WhatsApp-Plugins-Ecosystem-for-Overwhelmed-Professionals
WhatsApp and other messaging apps have become the defacto place where business is done. Why not make it work?
Salute: An AI design system generator that generates as you code.
The Design System to Engineering Handoff is clunky for most situations. Instead, designers vibe create design systems, and engineers vibe contribute. Managed through MCP
Maintain a Dynamic Project Viewer
A dynamic project viewer can handle multiple artifacts, file formats, and make it easier for clients to navigate projects.
Churn: An AI content editor for the Internet has been missing.
Content Management Systems are an old paradigm, they are clunky, they are rarely where creatives develop content. HTML and CSS need to marry Content Editors
Clean Specific Issues in YAML One at a Time
Targeted scripts to address specific YAML frontmatter issues for improved content management
Filesystem Observer for Consistent Metadata in Markdown Files
Let content teams develop content. Handle frontmatter inconsistencies gracefully for a seamless user experience.
corpora-builderai-labs15
Header Chrome
The workspace becomes a switcher, not a label. The mode toggle shows one icon and says what the next click gets you.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
corpora-builder/specs
astro-knots12
Dynamic Portfolio Page Specification and Implementation Plan
Three clickable levels — logo grid, expanding card, detail page — with a passcode gate that reveals placeholders, not real data.
Versatile Component Library for Video Players
Videos links can come from various sources, and include metadata, playlists, and other information that handled to maximize the value of video content, all from simple markdown triggers.
Include Full Search as a Default
Search ships from the first build via `astro-pagefind`, not at some size threshold. Seven surfaces have it; fifteen do not.
Image Catalog and ImageKit Hosting for Arthouse
The repo stays public because it holds metadata only; ImageKit holds the bytes, and a privacy tier keeps NSFW originals out of the output.
Polish Pass for Arthouse Site
Takes arthouse-site from scaffold-complete to client-presentable, with an AI photo-to-illustration pipeline for sensitive source material.
Codifying a Comprehensive Extended Markdown Flavor and Shared Package
A named, versioned markdown flavor that codifies what we already render, backed by one shared remark/rehype package.
Remark-Citations: A Unified Plugin for Hex-Code Footnote Management
A standalone remark plugin that transforms footnote identifiers (hex codes, numeric, or mixed) into sequentially-numbered citations with structured metadata parsing, designed for the unified/remark ecosystem and bundled into @lossless-group/lfm.
Create an Image-Heavy Portfolio Website for Boutique E-Commerce
A mobile-first, image-heavy portfolio site: carousel galleries, tiered pricing cards, WhatsApp CTA, all managed through markdown.
Portfolio-Wide Job Aggregator
A specification for scraping, aggregating, and displaying job openings across a venture capital firm's portfolio companies — built as a reusable pattern for any VC client site.
Context-V GitHub Fetcher for Multi-Repo Content Aggregation
A build-time fetcher that pulls context-v documents from ~20 repos, so lossless.group can render them without copying or submodules.
Develop a Slides-only Astro Site for a Fundraise Process
A slides-only Astro site that stays consistnent with relevant Context Vigilance files fed into AI Assistant context.
astro-knots/specs
lfm9
Maintain Project Task Management with LFM
One checkbox line that reads correctly in Obsidian and on GitHub, and only becomes queryable data when LFM is asked.
Maintain Path Resolution for Wikilinks
How vault paths become site routes — the index cascade, why ambiguity refuses to guess, and the rule that every judgment call is a config field rather than a decision baked into the package.
Maintain Eyebrow, Heading and Subheading Blocks
Cards have had a three-part heading for years — eyebrow, heading, subheading — and long articles need it more than cards do. Three adjacent lines, one semantic unit, one `<hgroup>`, and only the middle one ever reaches the table of contents.
Maintain Heading Anchors And Share Links
A fragment URL is a public contract, and we currently ship two incompatible definitions of it. This moves anchor identity into LFM as data, leaves the share affordance in the render layer, and fixes collisions nobody is handling.
Maintain an Elegant Markdown and Extended Markdown Render Pipeline
Render AST in Debug
Exploration of AST structure at each stage of markdown processing to understand how to handle callouts
Maintain Figma Object Embeds Using Embed Kit
Embed live Figma files, frames, and prototypes inside markdown via the `:figma-embed` text directive — width, height, and auth-user as attributes.
Maintain Directives In Extended Markdown Render Pipeline
Directives bring MDX like component rendering using special extended markdown syntax.
lfm/specs
memopop-orchestratorai-labs / memopop-ai7
MemoPop Connector API
Ten tools, one step registry, and the docs and tests that ship with each. What we build so a partner's Claude can write a MemoPop memo.
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.
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.
PDF Parser Agent Specification
A small specification for an agent and script to parse PDFs and convert them to markdown with properly formatted citations.
Multi-Agent Orchestration for Investment Memo Generation
An exploration into using AI supervisors and specialized agents to generate high-quality content and documents.
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.
memopop-orchestrator/specs
content-farm5
Per-Directory Profile Templates — v0.1 Spike
One Perplexity call per file, four template zones, and `***` as the scratch terminator — aborts rather than merge if the body has prose.
Metafetch source notes — fetch from any journal URL, not just `url`
A note about a paper keys its link as `arxiv:`, not `url:` — and metafetch couldn't see it. A URL picker across every frontmatter property, a scholarly metadata tier, and vault-wide identity codes now make a source note worth having.
Stenographer: an Obsidian Plugin that Transcribes Audio Content
Drop a YouTube, SoundCloud, or other listenable link into Obsidian and Stenographer turns it into a fully-frontmattered note with a streaming, AI-generated transcript — sources become searchable knowledge in one move.
Github Splash Page for Content Farm
An in-repo Astro site that turns the content-farm pseudomonorepo into a public landing page — hero, plugin gallery, changelog and context-v rendering — deployed for free off GitHub Pages while we wait for a real marketing surface.
content-farm/specs
ai-labs4
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.
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.
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.
ai-labs/specs
context-vigilance-kitai-labs4
Survey: a Scoped Dashboard of context-v
One command turns every context-v/ folder in scope into a dashboard, a task list, and a map, the way graphify turns code into a graph.
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.
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/`.
context-vigilance-kit/specs
cite-widecontent-farm4
Enrich Citations
One command fills in every citation's missing title, author, date, publisher, and brand assets — and shows you every change before it writes.
Promote to Canonical Source
One command turns a source you'll cite again — a book, a report — into a rich record with its file and full text in your vault.
Modal for Pasting LLM Native Content
Stop the parsing problem at the source: a paste-target textarea plus a Google/Perplexity selector, feeding the parser at the cursor.
cite-wide/specs
self-host-stack4
Homebase MCP — one connector per client, every tool behind it
A client adds one address to Claude and their agent can move across CRM, wiki, data room, and post planner in a single task — because one plane fronts them all, authenticates them through didi.sh, holds the credentials, and serves our skills as both prompts and resources.
Per-Client Stack Deployment — Twenty First (reach-edu, then palmer-ai)
Stand up Twenty CRM for reach-edu, then palmer-ai, on Railway project-per-client — phase by phase, with a verification gate at every step.
Papermark Self-Hosted Dataroom Deployment
Complete deployment specification for self-hosting Papermark as an open-source virtual data room for sharing investment memos, pitch decks, and due diligence documents.
self-host-stack/specs
lossless-changelogastro-knots3
Aggregate Changelog Streams Across the Lossless Tree via the GitHub API
One hand-maintained collection becomes a live aggregation over 38 changelog streams, each pulled from its own repo at its own branch.
Extract the Lossless Brand Layer from lossless-site
The brand is worth keeping; its token system isn't — 14 Google fonts loaded to use none. Extract it into two-tier tokens, dark by decision.
lossless-changelog/specs
context-v-corpus3
The Corpus Splash as a Reading Room
The practice has its own site now. This one stops selling it and starts showing it: a thousand real context-v files, by kind and by project.
Systematizing Chroma as the Loading Mechanism for context-v
Chroma holds 5,224 context-v chunks and we still load context by hand. Three loops turn the corpus into a session-start loading system.
context-v-corpus/specs
flave-aiai-labs2
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.
flave-ai/specs
arthouse-siteastro-knots2
dark-matterastro-knots2
fullstack-vcastro-knots2
A Two-Perspective How-To Engine — Use-Cases ✕ Tool-Uses, Built on LFM (Not Starlight)
VCs arrive two ways: 'I need to automate dealflow' (a use-case) and 'I've heard I need Hermes Agent' (a tool). The same how-to should be reachable from both doors. This spec defines a docs engine on top of @lossless-group/lfm that renders one body of how-to content through two parallel navigation perspectives — with left-nav, right-hand TOC, prev/next pagination, wikilinks, callouts, citations, and video/GIF embeds — and deliberately does NOT adopt Astro Starlight.
fullstack-vc/specs
perplexedcontent-farm2
stenographercontent-farm2
A local transcription engine for Stenographer
Stenographer routes every job to a paid API, which is correct for public YouTube and wrong for a founder call. A third engine speaking the OpenAI transcription API against a user-supplied base URL covers whisper.cpp, Speaches and MLX in one integration — but it forces the pipeline's first real change: from URL-in to source-in.
stenographer/specs