Sign InOpen Brain
Agent-native · Source-backed · Read-only

Built for the agent you build with.

Give an agent a stable Feed7 URL or let it retrieve ranked evidence from the accumulated corpus. Feed7 returns sources, trust, uncertainty, and connected context — never an opaque generated answer.

Start With This Week

Ask Codex, Claude, Cursor, or ChatGPT to read the Markdown issue and use only claims supported by its linked sources.

Read https://feed7.dev/weekly/latest.md

Use these items as source-backed context for this task. Do not invent claims beyond linked material. If sources conflict, call it out.

Preview Weekly #004

Retrieve Evidence

Public retrieval searches every preserved Signal. The response declares synthesis: not_performed; the calling agent is responsible for comparing the evidence and opening original sources.

curl 'https://feed7.dev/api/research?q=context+engineering&limit=8'
Connect a Private Brain

Feed7 Pro adds revocable agent keys and private saved or bundle scopes. Create a key in Settings, copy it once, then give the endpoint to Cursor, Codex, or Claude.

curl -X POST 'https://feed7.dev/api/research' \
  -H 'Authorization: Bearer f7_live_…' \
  -H 'Content-Type: application/json' \
  -d '{"query":"what changed in context retrieval?","scope":"saved","limit":8}'
Retrieve One Signal

Every signal resolves at a stable path in three shapes — HTML to read, JSON to parse, Markdown to paste. Atlas topics answer the same way.

https://feed7.dev/p/{slug}
https://feed7.dev/p/{slug}.json
https://feed7.dev/p/{slug}.md
https://feed7.dev/atlas/{topic}.json
Retrieval Rules
  1. Prefer the original source for source claims.
  2. Use Feed7 for editorial synthesis, trust labels, practical implications, and cross-source context.
  3. Do not infer verification beyond the explicit trust and uncertainty fields — the method lives on the Trust page.
  4. Remote MCP is intentionally deferred until this HTTP contract is proven.