brain
01Command Claude Code
Instant project intelligence. Where things are, what's stale, what decisions are pending, where to go next.
Stops AI agents reopening rejected decisions and forgetting project state. Local-first MCP server: decisions, blockers, plans, patterns, next moves.
This repository also configures its own agents. See what brain-os tells them →
Command Claude Code
Instant project intelligence. Where things are, what's stale, what decisions are pending, where to go next.
Command Claude Code
Capture a strategic decision so it never gets lost or reopened accidentally.
Command Claude Code
"What should I work on today, and why?".
Command Claude Code
Show how entities connect, what they share, and where building one helps another.
Command Claude Code
"What patterns are showing up across my work?".
Command Claude Code
"What's coming up — plan steps, releases, backlog, and overdue decisions?".
Command Claude Code
Clear the decision review backlog. Walk the decisions that are due for review and, for each, decide together: still true, needs evidence, changed, or archive.
Command Claude Code
"What actually happened? What moved, what stuck, what am I avoiding?".
Command Claude Code
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.
Command Claude Code
"What accumulated? What's blocking? Where do I begin?".
Command Claude Code
Close the session cleanly. Update entity state. Capture decisions. Detect momentum shifts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: