PMB gives Claude Code, Cursor, Codex and Zed persistent project memory through MCP. It stores decisions, lessons, goals, recent work, project facts and docs in one SQLite workspace on your disk. No cloud, no API keys, no LLM call on the read path. It is open source, offline-first, inspectable/exportable, with a local dashboard and honest impact tracking so you can see which memories actually help.

Hi Product Hunt - I built PMB because every coding agent I used had the same frustrating loop: brilliant in one session, forgetful in the next. I kept re-explaining decisions, constraints, file history, and "please never do X in this repo again." PMB makes that memory local and durable. It stores decisions, lessons, goals, recent work and facts in one SQLite workspace on your disk, then feeds the relevant context back to Claude Code, Cursor, Codex, Zed and other MCP-aware agents. No cloud, no API keys, no hosted memory service. The design evolved from "just save notes for the agent" into typed memory: lessons are treated as rules, goals as goals, and project work as recent activity. The thing I care about most now is trustworthy memory: what should an agent remember automatically, what should it ignore, and how do we show when memory is actually helping? Would love feedback from people using coding agents every day. Fastest try: pip install pmb-ai && pmb setup

The re-explaining problem is genuinely painful. Every new Claude Code session starts with several minutes catching it up on decisions already made, directions already tried, and why the architecture looks the way it does. Having MCP-backed persistent context that retains all of that locally - no cloud, no API overhead on reads - is the right shape for this problem. The SQLite approach is smart for anything touching sensitive project details. Curious: how does it handle conflicts if two different agents write to memory simultaneously on the same project?

PMB | Local-first memory for AI

Stop re-explaining your project to AI coding agents

Stop re-explaining your project to AI coding agents