How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
AsenaJsReads credentialsllms.txtAsenaJs/Website/public/llms-full.txt
WebSockets, messaging and static or Bun-bundled HTML. It does not ship an opinionated frontend rendering layer. ## Related - [Get Started](/docs/get-started) - Build your first Asena application - [Dependency Injection](/docs/concepts/dependency-injection
AsenaJsllms.txtAsenaJs/Website/public/llms.txt
Cron-based background jobs with @Schedule and CronRunner, powered by Bun's native cron - [Frontend Controller](https://asena.sh/raw/concepts/frontend-controller.md): Serve HTML pages with @FrontendController and @Page using Bun's native
heptauReads credentialsllms.txtheptau/pgarachne/docs/llms-full.txt
SPAs) or the Explorer tool directly. This architecture dramatically simplifies the stack: Database ↔ PgArachne ↔ Frontend / AI Agent. Endpoint structure: All database endpoints share a common prefix (default `db`, configurable
Pseudogiant-xrReads credentialsllms.txtPseudogiant-xr/Pseudolife-MCP/llms-full.txt
# Pseudolife-MCP — full documentation > Persistent long-term memory for Claude Code, Codex, and other
sandraschillms.txtsandraschi/bumi-mcp/llms-full.txt
virtual-twin guidance, optional robot bridge. ## Ports | Service | Port | |---------|------| | Backend (FastAPI + MCP /mcp) | 10774 | | Frontend (Vite React) | 10775 | ## MCP Tools - `bumi_specs` — Hero robot specifications and capabilities - `bumi_links
sandraschiPipes a download into a shellllms.txtsandraschi/filesystem-mcp/llms-full.txt
# filesystem-mcp > **Complete guide to packaging and distributing MCP servers with MCPB** --- 📄 [MCPB_BUILDING_GUIDE.md](MCPB_BUILDING_GUIDE.md
sandraschiReads credentialsllms.txtsandraschi/filesystem-mcp/llms.txt
writes with per-path asyncio locks and automatic `.backup` files - Ports: backend 10742, webapp frontend 10743 (dev) - REST: /api/health, /api/status, /api/capabilities, /api/skills, /api/llm/discover, /api/llm/chat, /api/v1/diagnostics ## Docs - [Readme](README.md): Overview, quick
0spoonPipes a download into a shellllms.txt0spoon/seamless/docs/llms-full.txt
# Seamless > A local-first memory and coordination substrate for the fleet of coding agents
mrcbrbn5361Reads credentialsllms.txtmrcbrbn5361/SyncytiumMD/llms-full.txt
Obsidian-style visual brain graph of their rules, tags, and ADRs without installing heavy frontend runtimes (e.g. Next.js, Electron, or Express). **Decision:** Implement an embedded Canvas-based force-directed graph
nifrajsReads credentialsllms.txtnifrajs/nifra/llms-full.txt
required for a backend-only app. `bun add @nifrajs/core` ### A server - no frontend required Chainable and fully type-inferred. This is a complete app: `@nifrajs/core` alone is a production backend
nifrajsReads credentialsllms.txtnifrajs/nifra/llms.txt
Google Fonts downloader (the next/font equivalent) plus CLS-safe @font-face + preload primitives. - [Nifra - Frontend gotchas](/docs/frontend-guidance): Version-scoped React, Preact, Solid, Vue, Svelte, and Nifra frontend gotchas exposed through
opencuePipes a download into a shellllms.txtopencue/cuecards/docs/llms-full.txt
materialized runtime contains only that profile's resources. Marketing work doesn't see frontend MCPs; backend doesn't see design skills. == INSTALL == Primary: npm install -g cue-ai One-line
opencuellms.txtopencue/cuecards/llms.txt
background process. - Profiles inherit from a `core` baseline. 194 profiles ship by default (backend, frontend, marketing, cybersecurity, medusa-dev, …). - Ten agents supported via `cue materialize `: claude, codex, cursor, cline, gemini
sweenzorReads credentialsllms.txtsweenzor/roam-docs/public/llms-full.txt
encrypted graphs, offline graphs). - **Warning**: the backend can be a few changes behind the frontend while local changes are still syncing. - Return:: - Promise resolving to the query results - Example:: - ```javascript
sweenzorllms.txtsweenzor/roam-docs/public/llms.txt
/developer-documentation/data-model.md): Your graph is a DataScript database. - [Roam Alpha API](https://roamdocs.fyi/developer-documentation/roam-alpha-api.md): The frontend JS API (window.roamAlphaAPI): datalog q/pull, block & page CRUD, UI control, file storage - [Roam Depot/Extension
flavorgoodllms.txtflavorgood/Selective-Intelligence/docs/llms-full.txt
Features that exist in code but do not work for users Trace routes, navigation, frontend, backend, data, permissions, flags, and deployment instead of treating a file as a finished feature
KhaledSaeed18Reads credentialsllms.txtKhaledSaeed18/dotclaude/site/llms-full.txt
# dotclaude: every item in full > The complete text of every Claude Code skill, agent
littlebearappsllms.txtlittlebearapps/contextdocs/llms-full.txt
# ContextDocs — Full Documentation > Complete documentation content for LLM ingestion. Generated from llms.txt file references
LoomA8osAgentllms.txtLoomA8osAgent/a8-loom-coordinator/llms.txt
coordinator) as the autonomous senior engineer on a > software project — any language, any framework, frontend or backend. Its enforced > idea: **discover-then-reuse** — retrieve what the codebase already provides
nirholasllms.txtnirholas/carbide/llms-full.txt
/api/comps sold comps for a model, narrowed to ±3 model years public/index.html single-file frontend, no build step data/listings.json normalized corpus data/sold.json verified auction results ``` Everything derived (cohort medians, outlier
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
