Introduction
Agent Brain is a self-hosted shared memory layer for AI coding tools.
It is designed to:
- Store project knowledge in one place
- Retrieve relevant context across sessions
- Reuse prior work where appropriate
- Keep data on your machine or infrastructure
Core capabilities
- Persistent memory for decisions, patterns, errors, preferences, and project context
- Semantic cache for similar queries and repeated workflows
- Cross-agent context sharing through MCP and REST
- Local-first processing on infrastructure you control
- Memory governance for audits, deduplication, archiving, and consolidation
- Desktop app for stack lifecycle, dashboard, knowledge explorer, and cache monitor
Ports
| Service | URL |
|---|---|
| MCP | http://localhost:3100/mcp |
| REST API | http://localhost:9090/api/v1 |
| Health | http://localhost:9090/health |
Requirements
- No Docker required for the desktop app; Docker is optional for source or Compose deployments
- 8 GB RAM recommended
- Linux x86-64, macOS 12+, or Windows 10+
- Enough disk space for local models and service data