cortex

Persistent memory for Claude Code built on computational neuroscience — not just retrieval. 36 cited brain mechanisms consolidate what matters, keep it current as your project evolves, and reconstruct the right context at the right time — a living memory, not a flat RAG. Says "I don't know" when unsure, flags its own contradictions. Local-first, single-click MCP install.

Getting Started · Configuration · Examples · What's New · Science · Benchmarks · Wiki · Architecture

Companion projects:
cortex-beam-abstain (repo cortex-know-when-to-stop-training-model) — community-trained retrieval abstention model for RAG systems
zetetic-team-subagents — specialist Claude Code agents Cortex orchestrates with
automatised-pipeline — automated 11-stage pipeline (findings → PRs); Cortex ingests its codebase analysis via the optional ingest_codebase / change_impact tools
cortex-viz — read-only visualization MCP (galaxy graph, execution trace, wiki browser) over the same store

_{Independent project: Cortex is an independent, open-source project. It is not an Anthropic product and is not affiliated with, sponsored by, or endorsed by Anthropic.}

---

Claude forgets you every time you close the tab. Every architecture decision you explained. Every debugging session where you traced a bug through four layers of abstraction. Every "remember, we decided to use event sourcing, not CRUD" correction. Gone. Next session, you're a stranger to your own tools.

Cortex is a persistent memory engine for Claude built on computational neuroscience. It remembers what you worked on, how you think, what you decided and why — not as a text dump shoved into context, but as a living memory system that consolidates, forgets intelligently, and reconstructs the right context at the right time.

It runs entirely on your machine — a local SQLite database by default (zero setup, no services to install), or PostgreSQL + pgvector when you want it. A 22 MB embedding model, no LLM in the retrieval loop, no data leaving localhost.

36 neuroscience mechanisms · 50 memory tools · 9 lifecycle hooks · a self-curating, continuously-groomed per-project wiki — all local, all open-source.

---

Getting Started

Cortex ships as a single-click MCP bundle (.mcpb). Download the latest hypermnesia-mcp.mcpb from Releases, then open it in Claude Desktop — Settings → Extensions installs it in one click.

It runs immediately on the built-in SQLite backend: zero configuration, no database to provision, nothing to set up. Memory persists to a local file under ~/.claude/methodology/. That's the whole install.

Claude Cowork works the same zero-setup way: the sandboxed environment is detected automatically (CLAUDE_ENVIRONMENT=cowork) and Cortex uses the local SQLite store — no PostgreSQL required.

Want PostgreSQL + pgvector instead (for very large stores or a shared team database)? It's a single configuration field — see Configuration below. SQLite is the default; PostgreSQL is opt-in.