pax-beehive/paxm

436 stars · Last commit 2026-07-26

Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.

README preview

<div align="center">

# PAXM

### Stop re-explaining your project to every new coding-agent session.

[![CI](https://github.com/pax-beehive/paxm/actions/workflows/ci.yml/badge.svg)](https://github.com/pax-beehive/paxm/actions/workflows/ci.yml)
[![Release](https://img.shields.io/github/v/release/pax-beehive/paxm)](https://github.com/pax-beehive/paxm/releases/latest)
[![Go](https://img.shields.io/github/go-mod/go-version/pax-beehive/paxm)](go.mod)
[![Platforms](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-6f42c1)](https://github.com/pax-beehive/paxm/releases/latest)

PAXM carries decisions, conventions, and working context into later Codex,
Claude Code, OpenCode, Pi, Cursor, TRAE, Kimi Code, ZCode, Kiro, Cline, and MCP
sessions. Start locally with SQLite and no account, API key, embeddings, or
extra memory-layer model calls. Change memory providers later without rewiring
every agent.

[Install for Codex](#codex-plugin) · [Install the CLI](#opencode-pi-cli-or-mcp) · [See the result](#what-changes-after-installation) · [Docs](#documentation) · [中文](docs/README.zh-CN.md)

</div>

View full repository on GitHub →