agentleFS
youcislayoucisla/Agent-Foundry/web/llms.txt

Agent-Foundry / web

llms.txt1 starsChanged 23 days agoMITView on GitHub

Agent Foundry is an MIT-licensed, local-first skill runtime for AI coding assistants. It installs original, reviewable skills and agents into an existing harness and offers an optional local daemon and MCP server for planning, execution, logging, and verification. No cloud, no telemetry, no third-party skill content. Agent Foundry is an independent open-source project maintained by youcisla on GitHub. It is not affiliated with Microsoft Foundry, Manhattan Agent Foundry, or Infosys Agentic AI Foundry.

The file

Files
llms.txt
# Agent Foundry

> Agent Foundry is an MIT-licensed, local-first skill runtime for AI coding assistants. It installs original, reviewable skills and agents into an existing harness and offers an optional local daemon and MCP server for planning, execution, logging, and verification. No cloud, no telemetry, no third-party skill content.

Agent Foundry is an independent open-source project maintained by youcisla on GitHub. It is not affiliated with Microsoft Foundry, Manhattan Agent Foundry, or Infosys Agentic AI Foundry.

## Key facts

- npm: @youcisla/agent-foundry
- PyPI: agent-foundry-runtime
- MCP server: io.github.youcisla/agent-foundry
- License: MIT
- Runtime: local only; Python 3.10-3.14 and Node.js 22.14+
- Install: npx --yes --package @youcisla/agent-foundry agent-foundry-install
- MCP: uvx agent-foundry-runtime mcp
- Source: https://github.com/youcisla/Agent-Foundry
- Website: https://youcisla-agents.vercel.app/

## Pages

- [Homepage](https://youcisla-agents.vercel.app/): what it is, install lanes, verification
- [Skills and agents](https://youcisla-agents.vercel.app/catalog): every skill and agent, with a detail page per record
- [Docs](https://youcisla-agents.vercel.app/docs): install, verify, MCP, daemon, configuration, troubleshooting
- [Architecture](https://youcisla-agents.vercel.app/architecture): channels, components, harness roots, trust boundary
- [Why Agent Foundry](https://youcisla-agents.vercel.app/why): rationale, repository gates, explicit limits

## Machine-readable

- [Catalog JSON](https://youcisla-agents.vercel.app/data.json): skills and agents without body text, plus counts and revision
- [Build manifest](https://youcisla-agents.vercel.app/site-manifest.json): generated files, hashes, revision
- [MCP server metadata](https://raw.githubusercontent.com/youcisla/Agent-Foundry/main/server.json)
- [npm](https://www.npmjs.com/package/@youcisla/agent-foundry)
- [PyPI](https://pypi.org/project/agent-foundry-runtime/)

## Optional

- [GitHub repository](https://github.com/youcisla/Agent-Foundry): source, issues, contributing

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

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.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.