Claude Mega Brain

claude-mega-brain

*Loads the knowledge. Skips the search.*

100% accuracy · 0 tool calls · −66% tokens vs Obsidian+MCP

Real agentic sessions. Benchmark →

Install

Then in any project:

Start a new session — the knowledge base loads automatically.

The problem

Without claude-mega-brain, Claude guesses from training data:

With claude-mega-brain, the exact schema is injected at SessionStart:

Benchmark

10 questions with project-specific values unknowable from training data.
Real agentic sessions — not simulated.

† raw and Obsidian+MCP reach 100% agentic accuracy by using tool calls to explore the project — spending 3–4× more tokens and time. Without tools, they drop to 50% and 13%.

CLAUDE.md (raw files) matches mega-brain on accuracy but uses 25% more tokens and is 25% slower. mega-brain's compressed OKF index is smaller and faster — the gap widens as knowledge bases grow.

Full results · Reproduce

How it works

At SessionStart, a hook scans the entire project for any .md file with type: in its YAML frontmatter and injects a compact index:

No dedicated folder needed — documents can live anywhere in the project. When Claude reads an OKF file, linked concepts surface automatically via PostToolUse.

Zero overhead when not in use — if no documented concepts are found, the hook exits in

License

MIT — The shortest license that works.