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.
mbaileyllms.txtmbailey/voicemode/llms.txt
coding agents and automation) - [Extend Copilot Chat with MCP](https://docs.github.com/en/copilot/how-tos/provide-context/use-mcp/extend-copilot-chat-with-mcp): Connect MCP servers to Copilot Chat to share context from other applications. - [Use the GitHub MCP Server
No other project uses it yet
nucliwebllms.txtnucliweb/webperf-snippets/public/llms.txt
same URL without .md. --- ## Guides - [WebPerf Snippets CLI](https://webperf-snippets.net/CLI.md) - [MCP server](https://webperf-snippets.net/MCP.md) - [What agents get wrong](https://webperf-snippets.net/agent-mistakes.md) - [DevTools extension](https://webperf-snippets.net/extension.md) - [Which snippet
obseillms.txtobsei/obsei/llms.txt
Slack, Jira or a webhook, and serves it to AI agents through an MCP server whose only write, a proposed issue, waits for human approval. It is a Python
No other project uses it yet
obseillms.txtobsei/obsei/website/llms.txt
Jira, Linear or a signed webhook, and serves it to AI agents through an MCP server whose only write, a proposed issue, waits for human approval. It is a Python
No other project uses it yet
mnemox-aillms.txtmnemox-ai/tradememory-protocol/llms.txt
from a venue, and the optional proxy sits in front of a broker's MCP server. Memory is organized in three layers: - L1 (Raw Trades): Every trade recorded automatically with
No other project uses it yet
brayonpiReads credentialsllms.txtbrayonpi/hexstellar/llms.txt
MCP (register the CLI as a local MCP server; tools hxs.analyze/compute/verify/inverse/explore) hexstellar mcp ``` Every response always carries its compute cost — `elapsed_ms` (the solver engine's own compute time
No other project uses it yet
sceneviewReads credentialsllms.txtsceneview/sceneview/llms.txt
/docs/ai-context/): how to hand this file to any assistant, and how to install the MCP server - [AI-assisted development](https://sceneview.github.io/docs/ai-development/): the prompts and workflows that produce code which
LING71671Reads credentialsllms.txtLING71671/open-reverselab/docs/llms-full.txt
选最短路径，同时备份备选路径。 ``` ## 节点执行口径 每个节点都按同一格式推进： ```text 入口信号: 从响应、源码、配置、日志或工具输出里看到什么 打点动作: 运行哪段脚本、哪条命令、哪个 MCP 工具 成功标志: 响应差异、凭证可用、权限变化、文件可读、Flag 出现 下一跳: Credential / Source / Admin / RCE / DB / Cloud
LING71671Reads credentialsllms.txtLING71671/open-reverselab/docs/llms.txt
Claude Code and Codex, using manifest checkpoints, kb_router, attack-network routing, and MCP tools to keep every round resumable. - [red · CAPTCHA Bypass Techniques and Automation](https://ling71671.github.io/open-reverselab/kb/red/ctf-website/techniques/01-recon/captcha-bypass.html)
Ataraxy-Labsllms.txtAtaraxy-Labs/weave/docs/llms.txt
Cosmetic vs structural change detection - Post-merge semantic + parse validation - LRU entity cache in MCP server (500 entries) - Configurable: WEAVE_TIMEOUT, WEAVE_MAX_DUPLICATES, WEAVE_REPO ## Architecture Cargo workspace with
Steady2 mentions in 2 weeks
No other project uses it yet
SceneViewReads credentialsllms.txtSceneView/sceneview-android/llms.txt
/docs/ai-context/): how to hand this file to any assistant, and how to install the MCP server - [AI-assisted development](https://sceneview.github.io/docs/ai-development/): the prompts and workflows that produce code which
1 project uses a version of this
ksimbackPipes a download into a shellllms.txtksimback/hermes-ecosystem/llms-full.txt
embodiment in virtual environments | 8 | Experimental | | [gizdusum/hermes-blockchain-oracle](https://github.com/gizdusum/hermes-blockchain-oracle) | Solana on-chain analytics MCP server for Hermes | — | Experimental | | [Ridwannurudeen/hermes-council](https://github.com/Ridwannurudeen/hermes-council) | Adversarial multi-perspective MCP server for decision
ksimbackllms.txtksimback/hermes-ecosystem/llms.txt
official aarch64 Docker image. - [Install on a VPS](https://hermesatlas.com/guide/install/vps/): The always-on server setup — sizing, Docker vs direct, and the mandatory-auth security guidance. - [The Hermes Agent Memory
Auriti-Labsllms.txtAuriti-Labs/geo-optimizer-skill/site/llms.txt
geoready.dev/docs/schema-injector/): Generate and inject JSON-LD structured data (WebSite, FAQPage, Article, Organization) ## Integrations - [MCP Server](https://geoready.dev/docs/mcp-server/): Use from Claude Code, Cursor, Windsurf — 10 tools and 5 resources
Steady2 mentions in 2 weeks
No other project uses it yet
reticlehqPipes a download into a shellllms.txtreticlehq/reticle/llms.txt
from the inside, without screenshots. It is a > dev-only SDK plus a local MCP server / CLI that reads **program truth** (network, state, console, > routing, animations, framework state, React source
Steady3 mentions in 2 weeks
No other project uses it yet
asheshgoplaniPipes a download into a shellllms.txtasheshgoplani/agent-deck/llms-full.txt
Fork your forks to explore as many branches as you need ### MCP Manager Attach MCP servers without touching config files. Need web search? Browser automation? Toggle them on per project
asheshgoplaniPipes a download into a shellllms.txtasheshgoplani/agent-deck/llms.txt
forking**: Fork Claude Code conversations to explore different approaches in parallel - **MCP Manager**: Toggle MCP servers per session without editing config files - **MCP Socket Pool**: Share MCP processes across sessions
fastcrwPipes a download into a shellllms.txtfastcrw/crw/docs/llms-full.txt
response: "http"|"lightpanda"|"chrome"|"chrome_proxy"|"playwright"|"pdf"|"http_only_fallback" ================================================================================ ## PART 7: MCP SERVER (11 TOOLS IN PROXY MODE, 9 EMBEDDED) ================================================================================ Package: crw-mcp (npm: npx crw-mcp | cargo
Steady11 mentions in 2 weeks
1 project uses a version of this
fastcrwReads credentialsllms.txtfastcrw/crw/docs/llms.txt
Machine-readable API contract: https://docs.fastcrw.com/openapi.json - Agent skill manifest: https://docs.fastcrw.com/agent-onboarding/SKILL.md - MCP server (Claude Code, Cursor, Windsurf): `npx crw-mcp` — https://www.npmjs.com/package/crw-mcp - Official SDKs: Python `pip install
Steady11 mentions in 2 weeks
1 project uses a version of this
stoolapllms.txtstoolap/stoolap/llms.txt
ANALYZE orders; -- statistics for the optimizer EXPLAIN ANALYZE SELECT ... ; ``` ## For AI coding agents: the MCP server Stoolap ships an MCP server (`@stoolap/mcp`, 30 tools: query, execute, batches, transactions, schema inspection
No other project uses it yet
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.
