claude-brain

[](https://github.com/mikeadolan/claude-brain/actions/workflows/test-setup.yml)

Tested on: macOS, Ubuntu, Windows (automated CI) | Fedora 43 (primary development)

Introducing claude-brain for Claude Code - Your AI finally has a real memory. Not just RAG, RAG and beyond. 100% lossless recall across every session and every project, no silos. Local SQLite. Keyword, semantic, and fuzzy search across everything. Emails you a daily briefing, weekly portfolio, and project status reports - no other tool does this. Zero cloud dependencies. Your data never leaves your machine. Zero token burn. Unlimited potential.

Watch the explainer video: claude-brain in 85 seconds

---

Claude Code starts every session from zero. Close the terminal and everything is gone.

• Re-explain who you are every single session
• Re-state decisions you already locked weeks ago
• Lose track of what happened across sessions and projects
• MEMORY.md has a 200-line cap - Claude's built-in memory is a Post-It note
• Context compaction throws away your earlier conversation mid-session
• Projects are siloed - what you discussed in one project is invisible in another

Other tools exist, but most use lossy approaches - extracting AI-chosen summaries, discarding context, siloing memories per project. When you need to find exactly what was said three weeks ago across two different projects, those tools fail.

---

claude-brain is a RAG system - but that's just one layer. Here's what "beyond" means:

| What | How | |------|-----| | RAG (context injection) | Every prompt gets relevant memories injected automatically - hooks search your history before Claude sees your message | | Full lossless capture | Other tools extract "memories" and throw away the raw data. We keep every word. Nothing su