Show HN: BrainBox – Hebbian memory for AI coding agents

Hebbian memory for AI coding agents. Learns which files you access together, which errors lead to which fixes, and which tool chains you use most — then recalls them instantly.

Not a vector database. Not RAG. Procedural memory.

That's it. The postinstall script automatically:

BrainBox learns passively from your next Claude Code session. No configuration needed.

The macOS daemon (system-wide FSEvents file watcher) is completely separate and opt-in:

The daemon watches file changes across all your editors — not just Claude Code. It requires explicit opt-in because it registers a LaunchAgent and monitors your configured project directories.

Kill cold start by bootstrapping from your existing git history:

This seeds the neural network from git commit co-changes and import graphs so BrainBox starts with knowledge instead of from zero.

BrainBox implements neuroscience-inspired learning:

https://github.com/thebasedcapital/brainbox/raw/main/assets/brainbox-animation.mp4

https://github.com/thebasedcapital/brainbox/raw/main/assets/brainbox-spreading.mp4

https://github.com/thebasedcapital/brainbox/raw/main/assets/brainbox-superhighway.mp4

https://github.com/thebasedcapital/brainbox/raw/main/assets/brainbox-immune.mp4

If you're not using Claude Code, you can run the MCP server standalone:

Add to ~/.config/kilo/config.json:

BrainBox can be deployed as an OpenClaw memory slot plugin. See NeuroVault for the reference implementation.

Files accessed together form synapses. Access auth.ts then session.ts 10 times and BrainBox learns they're related — recalling one activates the other.

When you fix a bug, BrainBox remembers which files fixed which errors. Next time a similar error appears, it suggests the fix files immediately.

After 20 Grep-Read-Edit chains, BrainBox predicts you'll Read after Grep and pre-loads likely files.

Strong synapses resist further strengthening (like real neural synapses). Prevents any single connection from dominating the network.

Files recalled but never opened get progressively stronger decay. Consecutive ignores escalate: 1st = 10%, 2nd = 19%, 3rd = 27%. Opening the file resets the streak.

Identify the most-connected neurons in your network and detect decaying superhighways before they fade.

Auto-tag file neurons by project. Recall scoped to current project reduces cross-project noise.

Full details in WHITEPAPER.md.

MIT