Browse / Software development / mnemosyne
mnemosyne
Nabzx
Version control for AI agent memory.
Open Nabzx/mnemosyne → On the boundary of the four rules.
agent-memoryaiai-agentslanggraphllmmcpmulti-agentprovenancerustversion-control
Works with any agent
ships AGENTS.md, the cross-tool instruction file.
In its own words
Commit, branch, merge, blame and time-travel what your agents know.
Version control for AI agent memory.
An AI agent builds up memory as it works: facts it learns, decisions it makes. Frameworks store that as state it overwrites as it goes. Mnemosyne gives agent memory what Git gives code: blame, bisect, commits, branches and merge. A Rust core, a mnem CLI, and a Python SDK. Local, deterministic, no network, no model calls.
The problem
Your agent runs for an hour, makes forty tool calls, and updates its memory the whole way. Then it gets something wrong, and all you have is the memory as it stands right now. You cannot see when the bad fact got in, what the agent knew before it went off track, or why it believes what it believes. Version control solved exactly this for code.
What you get
Every correctness property above - exact reconstruction, precise bisect, accurate blame, no lost writes on merge - holds at 100% across an 80-seed, 720-run sweep, plus a separate 50,000-case fuzz test on the merge algorithm, gated in CI on every change. Full detail: the benchmark.
A handful of newer, more exploratory commands sit alongside these: mnem contradicts flags likely direct negations in working memory, mnem approve/mnem reject run a review step over a branch before it merges, and mnem registry publish/fork shares a whole agent as one portable bundle.
Quickstart
Already have Rust? cargo install mnem-git builds the CLI from source instead.
Three commands, and an agent's memory is under version control:
The repository's own description, then 36% of its README. Read the rest on GitHub ↗
Read from the repository's git tree on 2026-08-17.