Skip to content
Tech News
← Back to articles

Show HN: PMB – local memory for coding agents that shows if it is used

read original more articles
Why This Matters

PMB offers a privacy-focused, high-performance local memory solution for coding agents, ensuring data never leaves the user's machine. Its hybrid recall system seamlessly injects relevant memory without slowing down agent responses, supporting multiple operating systems and popular agent frameworks. Additionally, it provides self-assessment features to maintain memory quality, making it a valuable tool for secure and efficient AI development.

Key Takeaways

FAQ Straight answers

Does my code or data ever leave my machine? No. Everything lives in a local SQLite file with vectors in LanceDB right next to it. There are no network calls on the read path, no account and no telemetry, ever. Unplug the internet and it still works.

How is this different from RAG or a vector database? Two ways. Recall is hybrid, BM25 plus dense vectors plus an entity graph, fused and ranked. And it's automatic: the right memory is injected before the model thinks. You don't build a pipeline or hope the agent remembers to call a tool.

Will it slow my agent down? No. Recall lands in about 35 ms and writes return in under a millisecond, the embedding and vector insert happen on a background thread, so the turn is never blocked.

Which agents and operating systems are supported? Any MCP-aware agent: Claude Code, Cursor, Codex, Zed, Windsurf and more, wired in with one command. PMB is pure Python and tested on macOS, Linux and Windows.

What if a memory is wrong or unhelpful? PMB scores whether each lesson actually gets followed and flags the dead ones so you can prune them. It's the rare tool that tells you when its own memory isn't earning its place.