ExternalBrain — AI skill for Claude Code
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilot, any MCP client).
How to install ExternalBrain
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open bejranonda/ExternalBrain and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What ExternalBrain does
Self-improving, self-hosted memory across every AI coding tool, project, and team (Claude Code, Cursor, Copilot, any MCP client). Autoskill proposes new skills from your sessions, so each project improves automatically. Inspectable, grounded, and yours. Built for teams and enterprise. Open source, MIT.
Alternatives in AI
- Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★
- Orkas — Open-source multi-agent AI desktop client — build and command your AI agent team through conversation 1.5k ★
- Agenvoy — Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets 474 ★
README
External Brain: Self-Improving, Compounding AI Coding Intelligence Across Every Tool, Project, and Team
**Standard AI memory is trapped in one tool, one project, one person — and stays static.** Claude Code doesn't share with Cursor, lessons learned on one repo don't carry to the next, and basic memory just accumulates raw chat history. External Brain is **a self-improving, compounding intelligence engine across every MCP tool, project, and team**. It extracts structured rules and recipes from finished sessions, reinforces what pays off, decays obsolete guidance, and doubles the power of every AI tool from your team's real work. Built for teams and enterprise, on your own infrastructure.
Related Skills
Mnemon
Self-hosted, cross-device long-term memory for AI agents via MCP — one vault shared across any MCP client (Cla
Montycat MCP
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live upd
Recollect
Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessi
Provena
Self-hosted memory for AI agents via MCP. Capture source events, retrieve context across sessions, and explain
Universal Memory
Self-hosted, markdown-first memory for LLM agents across devices and sessions
Crbro Memory
CRBRO — persistent neural memory for AI agents (MCP server): a file-based brain with neurons, synapses and hea
Related Agents
Auditor Agent
Self-improving auditor. Reads persona evaluation traces and proposes bounded, evidence-driven optimizations to
Cursor Delegate
Proactively use when this coding agent should hand a substantial coding, diagnosis, or implementation task to
Cursor Rescue
Proactively use as an extra agentic lane on Cursor's own quota — bounded coding tasks (a spec file, a rename,