Setup GBrain
Set up GBrain from scratch. Target: working brain in under 5 minutes.
Installing into an agent harness? (Claude Code, Codex, OpenClaw, etc.)
gbrain bootstrapis the paste-in install path — it wires hooks, the maintenance sweep, and harness config in one command. On a box that already hosts a brain + a runninggbrain serve --http(agent-framework boxes),gbrain bootstrap harness --yeswires framework-spawned Claude Code/Codex sessions instead — no agent workspace needed. See https://github.com/garrytan/gbrain/blob/master/docs/guides/bootstrap.md. This skill covers the brain-side setup (database, sync, first import); the two are complementary.
Contract
- Setup completes with a working brain verified by
gbrain doctor --json(all checks OK). - The brain-first lookup protocol is injected into the project's AGENTS.md or equivalent.
- Live sync is configured and verified (a test change pushed and found via search).
- Schema state is tracked in
~/.gbrain/update-state.jsonso future upgrades know what the user adopted or declined. - No Supabase anon key is requested; GBrain uses only the database connection string.