The 8 organ systems
The AIOS Team Brain is organized as eight organ systems — independently deployable capabilities that together form a collective intelligence layer. This page adapts the architecture model from Chetan’s product deck for the public OSS audience.
Status legend
Section titled “Status legend”| Symbol | Meaning |
|---|---|
| ✅ Shipped | MVP in the current tagged release |
| 🟡 Partial | Schema or engine exists; gaps remain (see notes) |
| ⬜ Planned | On the roadmap; not yet in production code |
The organs
Section titled “The organs”1. Knowledge repository — ✅ Shipped
Section titled “1. Knowledge repository — ✅ Shipped”Everything the team knows, structured and retrievable. Items land in Postgres with full-text search; the query layer assembles context for natural-language answers.
Where: items table, FTS indexes, lib/query in the Team Brain.
2. Ingestion layer — ✅ Shipped
Section titled “2. Ingestion layer — ✅ Shipped”Pipes from workspace pushes and external sources into the brain. The CLI sync path and Python sidecar handle tier-tagged writes at the API boundary.
Where: lib/ingest + ingestion/ sidecar. Eight source types in MVP.
See also: Brain API v1 for the sync contract.
3. Context management — 🟡 Partial
Section titled “3. Context management — 🟡 Partial”Decides what surfaces and what stays quiet — signal over noise so the brain informs without overwhelming. Retrieval and ranking logic exists; prioritization heuristics are still evolving.
Where: lib/query/retrieve.ts in the Team Brain.
Related landing topic: Honesty — context overload (hard problem #1).
4. Action layer — 🟡 Partial (MVP)
Section titled “4. Action layer — 🟡 Partial (MVP)”Policy-gated agents that act on behalf of the collective. The schema and API seam exist; a full autonomous runner is not wired yet.
Where: lib/actions, actions table, POST /api/v1/actions.
See: Harnesses for how workspaces orchestrate agent work today.
5. Identity & membership — ✅ Shipped
Section titled “5. Identity & membership — ✅ Shipped”Who belongs, with what role and permissions. Teams, members, and per-member API keys are the root of access control.
Where: teams, members, api_keys tables.
See: Access tiers in the glossary and the tier model in Brain API v1.
6. Policy engine — 🟡 Partial
Section titled “6. Policy engine — 🟡 Partial”The constitutional layer — what’s autonomous, what needs approval, who decides. Engine and schema exist; dashboard UI and write-path enforcement are not complete.
Where: lib/policy, policies, approval_requests tables.
Principle: Permissioned (landing page).
7. Audit log — ✅ Shipped
Section titled “7. Audit log — ✅ Shipped”Immutable record of every action, query, and ingestion event. Append-only, trigger-backed — the trust layer for a shared brain.
Where: audit_log table in the Team Brain.
8. Feedback loop — 🟡 Partial
Section titled “8. Feedback loop — 🟡 Partial”Closes the loop so the brain learns from outcomes over time. PM sync, work events, and codebase analytics feed progression signals; full closed-loop learning is still maturing.
Where: work_events, lib/pm-sync, codebase scan ingest.
See: Agentic Engineering maturity for individual and team instrumentation.
How the organs connect
Section titled “How the organs connect”Workspace pushes (tier-tagged) │ ▼ Ingestion ──► Knowledge repository ◄── Context management │ │ │ │ ▼ │ │ Query / Surfaces │ │ │ │ ▼ ▼ ▼ Audit log ◄── Policy engine ──► Action layer │ │ └──────── Feedback loop ◄──────┘For deployment and operation, start with Team Brain and Your Workspace.