Project history, mapped into agent-ready context.
The Stream is what's new. The Atlas is what's connected. Knowledge Atlas links decisions, lessons, code, docs, tasks, sessions, and project history into a queryable graph so agents find the right context, not just the most recent context.
Decisions and lessons live next to the code, docs, sessions, and tasks they affect.
Most "memory" tools store snippets. The Atlas stores relationships — so when an agent reads auth/session.ts, it also sees the decision that shaped it, the lesson that constrains it, and the open task that depends on it.
Code ↔ decisions
Every file gains the decisions, trade-offs, and lessons that shaped it. No more re-deriving why.
Lessons ↔ guardrails
Lessons promote into guardrails on the surfaces they protect. Same fact, two roles.
Docs ↔ sessions
Indexed READMEs and runbooks attach to the sessions that actually used them.
An agent asks. The Atlas answers with the right slice.
Code graph. Knowledge graph. Same Atlas.
The relationships between files, concepts, decisions, and lessons live in one graph. Toggle the view; the underlying truth is the same.
Files, symbols, callsites, ownership.
Imports, references, and ownership graphs derived from the source — sanitised, never stored.
Decisions, lessons, sessions, threads.
Wisdom nodes connected by who learned them, where they were used, and which code they protect.
Every surface traverses the same Atlas.
MCP traversal
MCP-compatible tools query the Atlas with scoped, source-backed responses.
ContextStream Code
The first-party CLI uses the Atlas before every edit, surfacing related context inline.
Capsules
Capsules are pre-traversed Atlas slices, scoped, expiring, and revocable.
Where the Atlas connects.
Give every tool the project context it should already have.
The Stream is what's new. The Atlas is what's connected. Start with one decision; the graph grows from there.