Attestor is no longer memory for your coding assistant.
For the last few months I built and shipped a memory layer, then watched three things happen. The editor vendors shipped memory for free. The benchmark race became a race about which LLM answers the question. And every serious conversation I had was about something else entirely: when many agents share one memory, who is allowed to write, who is allowed to forget, and can you prove it afterwards.
So that is what Attestor is now. Governed memory for multi-agent production meshes.
What that means in the code, not the deck:
Six roles gate write and forget before any backend is touched. Reviewers and monitors are read-only, because a reviewer that writes contaminates the evidence trail.
Every memory carries which agent wrote it, in which session, on whose behalf. Optional Ed25519 signatures, verifiable later.
Contradictions supersede instead of overwriting. Every fact has valid time and transaction time. You can ask what the mesh believed last Tuesday.
Forgetting a user writes the audit row first, then walks every store and reports per-backend counts. Partial failure is visible, never silent.
Tenant isolation on all three stores, not only the database.
And as of this week, the governance jobs themselves are durable: consolidation, derived-state repair, the forget saga, and retention sweeps run as Temporal workflows with retry policies and an operator UI.
Every row in the README names the file that enforces it, and the limits are written down next to the claims. That is the whole pitch. If your memory layer cannot show you the enforcing line, it is a policy document.
Self-hosted, MIT, Python.
If you run agent meshes in a regulated setting and this is the problem you have, I would like to talk.