01
Source registry
Every doc, repo file, note, transcript, and skill — catalogued with type, tier, tags, and freshness. The registry is the source of truth; indexes are rebuildable.
Pl. 01 — Company context layer
Every doc, repo, note, and skill, catalogued in one registry. Hybrid search, an agent-maintained wiki, and an MCP-native API on top.
Pl. 02 — Capabilities
What is canonical, what is stale, what is private — and how agents search, fetch, and write back.
Every doc, repo file, note, transcript, and skill — catalogued with type, tier, tags, and freshness. The registry is the source of truth; indexes are rebuildable.
Vector and keyword retrieval over chunked content, with metadata filters. Every hit cites its source so agents and humans know where knowledge came from.
An agent-written lattice of Markdown pages — entities, concepts, syntheses — that compounds knowledge instead of re-deriving it on every query.
One REST surface and an MCP server. ChatGPT, Claude, Cursor, and custom agents query the same context layer your team browses in the library.
Pl. 03 — Section
Clients speak HTTPS. The API fans out to a registry, object store, hybrid indexes, and an LLM wiki — each independently rebuildable.
Pl. 04 — Admission
Browse the demo library, or join the waitlist for a workspace of your own.