brainclaw privacy

Analytics only if you say yes.

The site works without analytics. If you opt in, we use analytics to understand what helps and what confuses people. No ads. No resale. No dark patterns.

Privacy details

🤝

Handoffs

Hand off mid-task without re-explaining everything.

soloteam handoffsmemory

The hardest moment in a multi-agent session is the boundary: agent A is 80% done, you switch to agent B (different model, different timezone, fresh session), and B has to figure out what was happening from chat scrollback. Information is lost every time.

A handoff is the snapshot you hand over instead. Tied to a plan and to the Git diff: what’s in the change, what’s still pending, what to verify before resuming. The next agent reads it, runs the preconditions, and picks up state without reconstructing the world.

brainclaw handoff "JWT refactor 80% done. Token-expiry test still failing on local clock skew." \
  --plan pln_xyz \
  --pre-condition "npm install fresh" \
  --post-condition "All src/auth/*.test.ts pass"

Handoffs are immutable, searchable, and surface automatically in the next session’s bclaw_context kind=delta. See async handoffs for the full pattern.