Self-improving · Governed · Bias-resistant
ai-memory turns AI agents from amnesiac chatbots into a coordinated workforce with a shared, governed, auditable institutional memory — what you need before you can trust AI to operate autonomously at scale. One Rust binary. Your infrastructure. Any LLM. Apache-2.0.
The problem
Every conversation starts from zero. The AI forgot what you told it yesterday, what it figured out last week, and every decision you made together. Across a team of agents it's worse: they each forget, redo each other's work, and leave no shared record of what any of them knew or did.
A long-term memory layer underneath your agents — durable, shared, and trustworthy. The difference between an employee who keeps an organized notebook (and can hand it to a teammate) and one who wakes up every morning with no recollection of the job.
For the CISO / CTO room
Built like infrastructure, not a demo — because autonomous AI at scale is where the value and the risk both live.
Append-only, hash-chained, Ed25519-signed ledger. Prove who recorded or changed what, and when — tamper-evident. Turns "the AI did something" into a defensible record.
Per-namespace policy (write / promote / delete / approve), signed rules, secure-by-default. A policy-check error refuses the write — no silent bypass.
Real cryptographic agent identities, mTLS, cert-chain delegation, replay protection. Enrol, scope, and revoke AI agents like service accounts.
SQLite (single binary, air-gappable, edge) or PostgreSQL + Apache AGE (scale, graph). Works with any LLM / embedding provider, switchable by config. Offline is first-class.
At-rest encryption (SQLCipher), per-memory encrypted envelopes, TLS in transit, SSRF guards. Secrets structurally barred from logs, audit, and capabilities.
Federation with quorum (W-of-N) agreement before knowledge becomes authoritative, per-agent quotas, and graceful load-shedding admission control.
Governance gates, attestation, and anti-monoculture controls that make "is our shared AI knowledge being corrupted or dominated?" visible and measurable.
Three interfaces (API, CLI, the MCP standard), a versioned wire/schema contract, lossless archive/restore, enforced engineering discipline. A 5-year foundation.
The wazoo tier
Most "AI memory" is a notepad. This is a self-improving cognitive substrate for non-human intelligence — it learns from its own learning, governs itself, proves what it knows, and actively fights the echo chamber.
enforce, a write whose required governance hook is missing is denied. You can't accidentally run ungoverned.The danger: if one LLM family does all the reflecting, its blind spots get laundered into "authoritative" knowledge and recursively reinforced — a monoculture echo chamber compounding bias into bedrock. (The DeepMind "From-AGI-to-ASI" audit's #1 structural risk.) The layered answer:
The NHI vision, in one line