Personal project intelligence system. Learns from multiple projects over time, identifies patterns across success and failure, and serves low-latency context to AI coding agents.
py -m pip install -e ".[vector,sync,dev]"
py -m projectbrain setup --data-dir .projectbrain
py -m projectbrain statusOn Windows, run scripts/install.ps1 for a one-shot install, or use py -m projectbrain if the CLI is not on PATH.
py -m projectbrain generate-sync-key # save as PROJECTBRAIN_SYNC_KEY
py -m projectbrain setup --export-dir ~/ProjectBrain-Sync --encrypt-exports
py -m projectbrain export-backup --encryptExports auto-copy to sync.export_dir after each backup when sync.auto_export is true.
- Installer —
projectbrain setup,verify-install,scripts/install.ps1 - Encrypted export — Fernet
.encbackups viaPROJECTBRAIN_SYNC_KEY(pip install -e ".[sync]") - Backup/restore — local zip backups in
.projectbrain/backups/(auto on session start) - Doctor / eval harness —
projectbrain doctoror MCPdoctor - Evolution adoption — feature-flag rollout with post-adoption eval gate
- Monthly digest —
projectbrain digest - Feature flags —
.projectbrain/config.yaml - MCP tools —
setup_workspace,export_backup,doctor,get_evolution_digest, and more
- Scoring engine — success, risk, momentum, value, fulfillment, technical debt
- Reflection pipeline — auto checkpoint reflections from project evidence
- Pattern extraction — cross-project keyword patterns (needs 2+ projects)
- Risk assessment — detected risk factors per project
Open this folder in Cursor; ProjectBrain MCP is configured in .cursor/mcp.json. Enable the projectbrain MCP server in Cursor Settings → MCP. Reload MCP after upgrades to pick up new tools.
- Local SQLite storage with event outbox
- Project, Decision, Reflection CRUD
- Charter markdown and git metadata ingestion
- CLI:
init,ingest,status
By default, ProjectBrain stores data at ~/.projectbrain/ (or %USERPROFILE%\.projectbrain\ on Windows).
MIT