# Contexo

> Contexo is version control for AI agent context — commit, branch, review and share the prompts, rules and MCP configs your agents run on.

Contexo is "GitHub for AI context." Each project keeps a versioned `.contexo/` knowledge base that AI coding agents (Claude Code, Cursor, and any MCP-compatible tool) push to and pull from over MCP — so every session and teammate starts already up to speed. The CLI and server are open source and self-hostable; a hosted dashboard is the paid layer.

## Key pages
- [Home](https://contexo.live/): What Contexo is, how it works, features, and pricing.
- [Pricing](https://contexo.live/#pricing): Hacker (free), Team (beta $5/owner/mo), Org (self-host, free).
- [Pricing — machine-readable](https://contexo.live/pricing.md): Plain-markdown pricing for AI agents.
- [Blog](https://contexo.live/blog/): Technical notes on version-controlling AI context.
- [GitHub](https://github.com/sugihAF/contexo): Open-source CLI and server (Go).

## Blog posts
- [Contexo in the wild — six bootstrapping scenarios for ctx migrate and ctx generate](https://contexo.live/blog/contexo-in-the-wild-bootstrapping/): Six situations teams actually hit when they adopt Contexo on a project that already exists — a mature repo with docs, a codebase with none, an overgrown CLAUDE.md, a wiki in another repo — plus what happens after the import, when a generated scaffold meets reality and a teammate corrects an imported page.
- [Under the hood: how Contexo bootstraps a knowledge base — without a single parser](https://contexo.live/blog/under-the-hood-bootstrapping/): Third in the Under the hood series: the two on-ramps that fill an empty Contexo repo. How ctx migrate discovers an existing knowledge base and ctx generate manufactures one from a code graph — sharing a single Detector/Catalog engine, a text directive, and one manifest, with the agent doing every judgement call.
- [Under the hood: how Contexo remembers your project — without keeping your secrets](https://contexo.live/blog/under-the-hood-secrets/): Second in the Under the hood series: a code-level walk through Contexo's data path. What actually crosses the wire when your agent pushes (a list of pages, not your transcript), why the raw session buffer never leaves your laptop, how your tokens are hashed, and the honest answer to 'does Contexo keep my API keys?'
- [Under the hood: how Contexo distills a session into versioned memory — without an LLM](https://contexo.live/blog/contexo-under-the-hood/): A deep dive into Contexo's engine: how the CLI and server stay LLM-free by handing distillation to the agent already in the loop (the push handshake), and how section-aware diffs make a page's history legible in a way git diff can't.
- [Contexo in the wild — six real scenarios, start to finish](https://contexo.live/blog/contexo-use-cases/): Six concrete scenarios where Contexo earns its place — walked through step by step, from the commands you run to the MCP handshakes your agent handles. Every step maps to what Contexo actually does today.
- [Hello, Contexo: version control for the context your agents run on](https://contexo.live/blog/hello-contexo/): The one idea behind Contexo, and why we're starting this blog: the context your AI agents run on is code now — so it deserves diffs, history, and one shared source of truth. Here's the “context tax” it solves, what Contexo is, and how it works.

## Optional
- [RSS feed](https://contexo.live/rss.xml): New posts as they publish.