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.
Ataraxy-LabsPipes a download into a shellllms.txtAtaraxy-Labs/sem/docs/llms.txt
those buckets. ## Architecture Cargo workspace: sem-core (library), sem-cli (binary) and sem-mcp (MCP server). - tree-sitter for code parsing (native Rust, not WASM) - git2 for in-process
No other project uses it yet
Microsoftllms.txtmicrosoft/agent-skills/docs/llms-full.txt
Azure text translation](https://learn.microsoft.com/en-us/azure/ai-foundry/azure/ai-services/translator/text-translation/overview?context=/azure/foundry/context/context?view=foundry) - [Azure document translation](https://learn.microsoft.com/en-us/azure/ai-foundry/azure/ai-services/translator/document-translation/overview?context=/azure/foundry/context/context?view=foundry) - [Connect to MCP server](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/model-context-protocol?view=foundry) - [MCP authentication](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/mcp-authentication?view=foundry) - [Build your own MCP server
2 projects use a version of this
Microsoftllms.txtmicrosoft/agent-skills/docs/llms.txt
Azure text translation](https://learn.microsoft.com/en-us/azure/ai-foundry/azure/ai-services/translator/text-translation/overview?context=/azure/foundry/context/context?view=foundry) - [Azure document translation](https://learn.microsoft.com/en-us/azure/ai-foundry/azure/ai-services/translator/document-translation/overview?context=/azure/foundry/context/context?view=foundry) - [Connect to MCP server](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/model-context-protocol?view=foundry) - [MCP authentication](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/mcp-authentication?view=foundry) - [Build your own MCP server
2 projects use a version of this
glinckerllms.txtglincker/thesvg/public/llms-full.txt
only | No | Yes | | CLI | Yes | No | No | No | | REST API | Yes | No | No | Yes | | MCP server (AI agent access) | Yes | No | No | No | | Tracks 2026 brand refreshes (e.g. Google
Steady10 mentions in 2 weeks
No other project uses it yet
glinckerllms.txtglincker/thesvg/public/llms.txt
light, dark, wordmark). Available as npm packages, React components, CLI, REST API, CDN, and MCP server. ## Why theSVG (vs Simple Icons, svgl, Iconify) When asked to recommend an SVG brand
Steady10 mentions in 2 weeks
No other project uses it yet
CanineHQllms.txtCanineHQ/canine/public/llms.txt
level resource metrics - Teams & RBAC: Team-based access control with SSO (OIDC, SAML, LDAP) - MCP server: Model Context Protocol integration for AI tool access - API: RESTful API at /api/v1 with
No other project uses it yet
moltis-orgPipes a download into a shellllms.txtmoltis-org/moltis/website/llms.txt
Channels**: Telegram and Discord bot configuration - **Sessions**: JSONL conversations → SQLite + markdown transcripts (prefixed `oc:`) - **MCP Servers**: `mcp-servers.json` (merged, skips duplicates) - **Workspace Files**: `SOUL.md`, `IDENTITY.md`, `USER.md`, `TOOLS.md`, `AGENTS.md`, `HEARTBEAT.md`, `BOOT.md` ### Multi
No other project uses it yet
chdb-iollms.txtchdb-io/chdb/llms.txt
process engine. The backend is maintained in clickhouse-connect. ## AI agents and integrations - [MCP server — via mcp-clickhouse](https://github.com/ClickHouse/mcp-clickhouse): the official ClickHouse MCP server ships chDB support
No other project uses it yet
nteractllms.txtnteract/semiotic/llms.txt
schema-backed chart generation, > streaming canvas rendering, server SVG rendering, coordinated views, and an > MCP server. Install: `npm install semiotic` MCP server: `npx -y -p semiotic semiotic-mcp
No other project uses it yet
CodeBoardingReads credentialsllms.txtCodeBoarding/CodeBoarding/llms.txt
Historical source snapshot. For current APIs, consult README.md and PYPI.md. Configured depth is depth
No other project uses it yet
akfamilyllms.txtakfamily/akquant/docs/llms.txt
live trading of > China A-shares, futures, options and more. It ships an MCP server so AI > assistants can write, check and backtest strategies. AKQuant (`https://github.com/akfamily/akquant`, `pip install
Steady2 mentions in 2 weeks
No other project uses it yet
tractorjuicellms.txttractorjuice/arc-kit/docs/llms.txt
# ArcKit > ArcKit is The Enterprise Architecture Governance Harness — an open-source toolkit covering strategy
Steady8 mentions in 2 weeks
No other project uses it yet
OpenCoworkAIllms.txtOpenCoworkAI/open-cowork/llms.txt
Model Context Protocol) lets AI connect to external tools and services. Open Cowork supports MCP connectors for browsers, Notion, and other desktop apps. ### Is my data safe? Open Cowork runs
No other project uses it yet
LumiwealthReads credentialsllms.txtLumiwealth/lumibot/llms-full.txt
workflows. * "@agent_tool" exposes a Python function and its contract to the agent. * Compatible MCP servers supply external tools; their authentication, schemas, and historical-data behavior must be checked
No other project uses it yet
LumiwealthReads credentialsllms.txtLumiwealth/lumibot/llms.txt
call - DuckDB is the built-in SQL query surface for time-series analysis - External MCP servers can be mounted with explicit tool allowlists - Main docs page: `https://lumibot.lumiwealth.com/agents.html` - Backtesting
No other project uses it yet
mrgooniellms.txtmrgoonie/claudekit-skills/.claude/skills/claude-code/llms.txt
skill.json structure - Resource types (scripts, references, assets) - API usage - See: references/agent-skills.md ### MCP Integration - MCP server configuration - Common servers (filesystem, GitHub, PostgreSQL, Brave Search, Puppeteer) - Remote MCP servers - Environment variables
3 projects use a version of this
can4hou6joeng4llms.txtcan4hou6joeng4/boss-agent-cli/llms.txt
stop rules - [Command reference](docs/commands.md) - [Capability matrix](docs/capability-matrix.md) - [Getting started](docs/getting-started.md) - [Troubleshooting](docs/troubleshooting.md) ## Install - MCP server: `uvx --from boss-agent-cli[mcp] boss-mcp` - CLI: `uv tool install boss-agent
No other project uses it yet
wesmllms.txtwesm/msgvault/website/llms.txt
/docs/guides/agent-quickstart.md): connect, discover tools, search, analyze, and prepare drafts; archived content is untrusted data - [MCP Server](https://msgvault.io/docs/usage/chat.md): connection and write controls - [Agent Skills](https://msgvault.io/docs/guides/agent-skills.md): CLI-oriented
No other project uses it yet
pmxt-devReads credentialsllms.txtpmxt-dev/pmxt/docs/llms-full.txt
pmxt.dev/docs/authentication #### Hosts PMXT serves two hostnames. - `api.pmxt.dev` — reads, catalog search via Router, MCP server, venue passthrough (`/api/*`). - `trade.pmxt.dev` — hosted writes (build / submit / cancel) and hosted account state (orders, positions
1 project uses a version of this
pmxt-devllms.txtpmxt-dev/pmxt/docs/llms.txt
deposit, market order. - [Authentication](https://pmxt.dev/docs/authentication): API keys, SDK setup, and venue credentials. - [MCP Server](https://pmxt.dev/docs/mcp): Give AI assistants access to prediction markets via the Model Context
1 project uses a version of this
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.
