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

📡

Right context, automatic

The right docs, decisions, and traps load automatically.

soloteambuilder contextmemory

The thing that wastes the most time in agent sessions: the agent doesn’t know what you decided last week, the trap you found Tuesday, or the plan that’s still in flight on this scope. So you copy-paste, you re-explain, you wait while the agent re-discovers the same problems.

brainclaw fixes this on the way in. When the agent opens a session on a scope, bclaw_context returns the workspace state already pre-shaped for the prompt: the relevant decisions, the open traps for these files, the plan in flight, the open claims. Ranked by relevance, sized to fit the prompt budget, formatted for the calling agent’s tier.

# At session start — agent reads the right context for the scope
bclaw_context kind=memory path="src/auth/"

# Or just what changed since last time
bclaw_context kind=delta since=sess_abc123

Nine profiles tune the shape (dev / dense / compact / copilot / quick / briefing / openclaw / ops / research). BM25 ranking means when memory grows past the token cap, the most relevant items survive — not just the most recent. Pair with project memory — what you capture is what the next session reads.