The problem isn’t longer context.It’s deciding what deserves context.

Four primitives. No answers.

Exactly four read-only tools over stdio JSON-RPC. Stateless, no server-side conversation state, no repository mutation, no answer field anywhere. Verified from Claude Code and from Codex.

Do the expensive work before the query.

A search engine does not read the world when the user asks a question. Neither should an agent’s context layer. Repository changes update the index; the query path then touches only the postings it needs.

A guard process proves the property rather than asserting it: with the corpus loader and the in-memory index builder made to raise, all seven requests still answered. The query path never touches them.

One real repository: the operator’s Vision7 store, 1,513 sources and 61,747 passages, measured 2026-08-17 from a fresh supabrain-api mcp process. This is a product smoke on a named snapshot, not a benchmark and not a general performance claim. The 0.083 s search was measured on a compacted copy of the store; on the operator’s un-VACUUMed 5.1 GB store file the same first search took 1.1 s.

61,747 passages indexed. A handful enter the model.

The index can be large. The live context should not be.

How many blocks a task actually needs is a function of the task, the scope and the budget, not a fixed number. Supabrain makes no token-savings and no answer-quality claim; it makes the selection explicit, budgeted and inspectable.

Not every node needs the whole project.

The graph decides who works.

Supabrain decides what they need to know.

A graph already draws execution boundaries. Those boundaries can also be context boundaries. Node A does not need Node B’s transcript; Node B should not inherit every file Node A opened.

Each node can start from a fresh context and receive only the evidence its bounded job requires. Durable structured results survive the node. Transient context dies with it.

Status: direction, not a shipped capability. The review of whether the existing compile contract can serve a bounded node without new tools is delivered with recommendation PARTIAL (four candidate revisions, ruling pending). The private three-node spike has not started. Supabrain is not a graph framework and makes no claim of superiority over graph systems.

Built by dogfooding, not demos.

12 genuine sessions · 5 private repositories · 9 real-use defects fixed · defect discovery, not a benchmark.

Four read-only tools. One SQLite file. No answer field.

supabrain_compile → package
  evidence_items       file · lines · evidence_id
  context_text         within a hard budget
  budget               43 / 700  (recorded demo run)
  freshness            current | stale | unverifiable
  exclusions           reason-tagged, with counts
  evidence_gap_status  visible when evidence is missing
  package_fingerprint  deterministic, timestamp-free
  answer_field_present false

What runs today. What is direction.

Boundaries matter.

• Local and trusted-local only. No hosted runtime, no public binding, no deployment claim.
• No answer generation, and no answer field in any output.
• No production, beta, enterprise or customer-data readiness claim.
• No answer-quality and no token-savings claim. Retrieval is lexical; freshness is repository-level and coarse; nested repositories are reported, not covered.
• Graph context and context lifecycle are direction, not shipped capability.
• Measured figures are product smokes on named snapshots. Negative and null results are retained, not removed.