projectbrain
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@projectbrainrun doctor and summarize any issues across my projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ProjectBrain
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.
Quick Start
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.
Encrypted off-machine sync
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.
Related MCP server: Memory MCP
Milestone 4 (Current)
Installer —
projectbrain setup,verify-install,scripts/install.ps1Encrypted 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 MCPdoctorEvolution adoption — feature-flag rollout with post-adoption eval gate
Monthly digest —
projectbrain digestFeature flags —
.projectbrain/config.yamlMCP tools —
setup_workspace,export_backup,doctor,get_evolution_digest, and more
Milestone 3
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.
Milestone 1
Local SQLite storage with event outbox
Project, Decision, Reflection CRUD
Charter markdown and git metadata ingestion
CLI:
init,ingest,status
Data Location
By default, ProjectBrain stores data at ~/.projectbrain/ (or %USERPROFILE%\.projectbrain\ on Windows).
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Local-first memory and continuity for AI coding agents. No cloud backend; optional hosted lane.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Project memory, semantic code search, and grounded agent context.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI coding assistants with persistent project memory to retain architectural decisions, code patterns, and domain knowledge across sessions. It stores data locally in a SQLite database, allowing agents to remember, recall, and manage project-specific context using full-text search.3 npmApache 2.0
- AlicenseAqualityBmaintenanceProvides persistent cross-session memory and full-text search for AI coding assistants, storing project context, decisions, and preferences while enabling searchable access to conversation history via local SQLite.81MIT
- AlicenseBqualityBmaintenanceTracks working context and code structure in a portable local SQLite database, enabling seamless context and task continuity across different AI coding tools.121MIT
- AlicenseNot gradedqualityBmaintenanceProvides a local long-term memory layer for AI coding tools like Cursor and Claude Code, enabling cross-session, cross-tool sharing of project facts, user preferences, decisions, and workflows.5 npm2MIT