CAPA is the package manager for AI coding agents. Declare your skills, tools, rules, sub-agents, MCP servers, and plugins once in capabilities.yaml, run capa install, and CAPA writes them into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 35+ other agents.
How to install capa?
infragate/capa
$git clone https://github.com/infragate/capaInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install capa by running `git clone https://github.com/infragate/capa`, then use it for the current task and follow its documentation at https://github.com/infragate/capa.
README.md
| 1 | <p align="center"> |
| 2 | <picture> |
| 3 | <source media="(prefers-color-scheme: dark)" srcset="assets/banner-dark.svg"> |
| 4 | <source media="(prefers-color-scheme: light)" srcset="assets/banner-light.svg"> |
| 5 | <img alt="CAPA" src="assets/banner-light.svg" width="280"> |
| 6 | </picture> |
| 7 | </p> |
| 8 | |
| 9 | <h3 align="center">Agentic Capabilities and Package Manager</h3> |
| 10 | |
| 11 | <p align="center"> |
| 12 | <a href="https://github.com/infragate/capa/releases/latest"><img src="https://img.shields.io/github/v/release/infragate/capa?style=flat-square&label=latest&color=6366f1" alt="Latest Release"></a> |
| 13 | <a href="https://github.com/infragate/capa/actions/workflows/test.yml"><img src="https://img.shields.io/github/actions/workflow/status/infragate/capa/test.yml?style=flat-square&label=tests&logo=github" alt="Tests"></a> |
| 14 | <a href="https://github.com/infragate/capa/actions/workflows/release.yml"><img src="https://img.shields.io/github/actions/workflow/status/infragate/capa/release.yml?style=flat-square&label=release&logo=github" alt="Release"></a> |
| 15 | <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License: MIT"></a> |
| 16 | <a href="https://github.com/infragate/capa/releases/latest"><img src="https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey?style=flat-square" alt="Platforms"></a> |
| 17 | </p> |
| 18 | |
| 19 | CAPA is the package manager for AI coding agents. Declare your skills, tools, rules, sub-agents, MCP servers, and plugins once in `capabilities.yaml`, run `capa install`, and CAPA writes them into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 35+ other agents. |
| 20 | |
| 21 | |
| 22 | https://github.com/user-attachments/assets/98442d19-44c9-43e6-b2c2-88156b189d5e |
| 23 | |
| 24 | |
| 25 | |
| 26 | ## Why CAPA? |
| 27 | |
| 28 | AI coding agents need rules, tools, and conventions — and right now those live scattered across CLAUDE.md, .cursor/rules/, AGENTS.md, MCP configs, and a half-finished internal doc. No two setups match. |
| 29 | |
| 30 | CAPA collapses it into one `capabilities.yaml` next to your code: skills, tools, rules, sub-agents, plugins. capa install fans it out to every provider in its native format — .cursor/rules/ for Cursor, .claude/agents/ and CLAUDE.md for Claude Code, AGENTS.md for Codex, and so on. Capa-managed marker blocks keep your hand-written content untouched. |
| 31 | |
| 32 | One file, version controlled, pinned by capabilities.lock, cached by SHA. The teammate who clones tomorrow gets the exact bytes you got today. |
| 33 | |
| 34 | ## What it does |
| 35 | |
| 36 | - One `capabilities.yaml` manages the content for your agent. Write rules, hooks, and tools once — capa runs them natively, supporting 35+ agents (Cursor, Claude Code, Codex, Windsurf, Copilot, Gemini CLI, and more). No more keeping `.cursor/rules/`, `.claude/settings.json`, and `AGENTS.md` in sync by hand. |
| 37 | - 19–40% cheaper inference, same quality. One MCP server per agent, tools lazy-load on demand instead of front-loading the whole catalog. Measured across 150 trials on claude-opus-4-8. |
| 38 | - Sub-agents only see the tools they need. Each gets its own filtered MCP endpoint — so your research sub-agent isn't holding a git push tool it shouldn't touch. |
| 39 | |
| 40 | <p align="center"> |
| 41 | <img width="1305" height="941" alt="CAPA Architecture" src="https://github.com/user-attachments/assets/a4db54a2-6ea5-43df-baa9-c61c189d30c1" /> |
| 42 | </p> |
| 43 | |
| 44 | ## Installation |
| 45 | |
| 46 | **macOS and Linux:** |
| 47 | ```bash |
| 48 | curl -LsSf https://capa.infragate.ai/install.sh | sh |
| 49 | ``` |
| 50 | |
| 51 | **Windows:** |
| 52 | ```powershell |
| 53 | powershell -ExecutionPolicy ByPass -c "irm https://capa.infragate.ai/install.ps1 | iex" |
| 54 | ``` |
| 55 | |
| 56 | ## Quick start |
| 57 | |
| 58 | ### 1. Initialize your project |
| 59 | |
| 60 | ```bash |
| 61 | cd your-project |
| 62 | capa init |
| 63 | ``` |
| 64 | |
| 65 | This creates a `capabilities.yaml` next to your code. |
| 66 | |
| 67 | ### 2. Install |
| 68 | |
| 69 | ```bash |
| 70 | capa install |
| 71 | ``` |
| 72 | |
| 73 | ### 3. Boostrap (Optional) |
| 74 | If you are already working on a project, and would like to get all of it's capabilities be managed by CAPA, simply use the `/bootstrap` skill. The agent will scan your project for skills, MCPs, relevant tools, hooks, and rules. |
| 75 | |
| 76 | `capa install` resolves SHAs and downloads anything that isn't already in the cache. I |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
