memlawb gives AI agents encrypted long-term memory
memlawb is an for AI agents that need to remember useful facts across work sessions. The memory is encrypted on the user's machine before it is uploaded, so the server stores only ciphertext and cannot read the content. The stays with the user, not with the server operator.
Teams can run the server themselves, using local file storage or S3-style storage. Any MCP-capable agent can add one block to get tools for saving, recalling, searching, listing, and deleting memories. Delta sync uploads only changed entries, and a local scanner checks for live-looking secrets such as before anything is encrypted and sent.
The project is in beta, with the server, client encryption, , MCP server, secret scanner, quotas, and implemented and covered by 50 tests. A free hosted beta is available at memory.gitlawb.com, but lost passphrases cannot be recovered because the host cannot read the data.
Key points
- memlawb gives AI agents memory that can persist across sessions.
- The server stores ciphertext, while the key stays on the user's machine.
- MCP agents can use tools to save, recall, search, list, and delete memories.
- Delta sync sends only changed memory entries.
- Losing the passphrase means the memory cannot be recovered.