markmhendrickson/neotoma

**Agents cannot own work they cannot verify.**
You cannot delegate real work to agents you cannot hold to account. Accountability has two halves: what was true, and who was authorized. **Neotoma is the system of record for AI agents** — it answers what was true. Your agents can produce a value; they cannot tell you its version, its source, or whether it is still current. Neotoma versions every fact, attributes it to a source, and replays it.
What ships today is the foundation: a deterministic, versioned state layer that ingests sources into immutable observations and computes reproducible entity snapshots with full provenance, exposed over an MCP server, a REST API, a CLI, and a bundled web Inspector. See Vision and execution status for exactly where the implementation stands against the vision.
It is built for developers building and operating AI agents who need a persistent, deterministic, auditable memory layer shared across tools. The same engine serves two further groups: individuals running a personal cross-assistant memory on a single-user install, and operators running a shared, multi-user instance with agent access control. Agents store structured records (contacts, tasks, transactions, decisions, events, and any other type) once and read them back across every tool and session, and the same observations always reduce to the same state.
**neotoma.io** · **Install** · **Documentation** (also served in-app at /docs)
Vision and execution status
As agent use expands, reality fragments across chat histories, agent memories, files, databases, tickets, and application state. The failure is not retrieval — it is that humans and agents can no longer answer: *which assertion is current? which source introduced it? was it observed, inferred, or decided? who had authority to correct it? which agents relied on the previous version? is there legitimate disagreement?* Neotoma's long-term role is **collective epistemic coherence**: not "better semantic memory," but deterministic, governed, multi-party state that humans and agents maintain together — attributed, correctable, disagreement-aware, portable, and independent of any one model or application.
| Vision phase | What it means | Status |
| --- | --- | --- |
| **P0 — Deterministic single-writer state** | Append-only observations, hash-derived IDs, deterministic reduction, field-level provenance, corrections-win, replayable history | ✅ **Shipped and stable** — the core guarantee, in daily use |
| **P1 — Multi-user state foundations** | Human and agent identities, attributed writes, tenant isolation, access controls, shared instances | 🟡 **Partially shipped**: hosted multi-user mode with user_id tenancy, per-agent identity (AAuth, optional hardware attestation), capability grants, guest tokens, peer federation. Not yet: organizations/workspaces, membership lifecycle, invitations, offboarding |
| **P2 — Authority over state** | Domain ownership, correction rights, supersession, policy ownership, temporary grants, disclosure logs | 🟡 **Mechanisms exist** (corrections always win, SUPERSEDES relationships, per-operation access controls); authority *semantics* — who may correct what, scoped by domain — are future work |
| **P3 — Multi-principal semantics** | Competing interpretations, disputed claims, official positions, consensus vs unresolved disagreement, field-level policies, historical validity | 🔜 Planned — interpretations are first-class today; dispute/official-position semantics are not |
| **P4 — Organizational intelligence substrate** | Non-developer governance UI, "why does the system believe this?" explanations, impact analysis, authority-graph views, enterprise administration | 🔭 Vision — the Inspector's provenance and audit views are the seed |
Ateles is the other half. Accountability has two halves: **Neotoma answers what was true** (truth, memory, provenance); **Ateles answers who was authorized** (initiative, delegation, approval) — against Neotoma state. Neither is sufficient alone. Memory without authority tells you what happened but not whether it was permitted; authority without memory tells you who may act but not against what state.
What Neotoma is
Neotoma is a state layer, not a chat memory or a vector cache. It records immutable observations from your sources, resolves them into entities, and computes a current snapshot for each entity by reducing its observations in a deterministic order. Nothing is overwritten. Corrections and reinterpretations add new observations; the prior history stays intact and replayable.