agentleFS
Sign inStart free
EconLab-AIEconLab-AI/Ultrabrain/CLAUDE.md

Ultrabrain

CLAUDE.md1 starsChanged 9 months agoMITView on GitHub

UltraBrain is a Claude Code plugin providing persistent semantic memory across sessions. It captures tool usage, compresses observations using the Claude Agent SDK, embeds them into LanceDB for vector search, and injects relevant context into future sessions. 5 Lifecycle Hooks: SessionStart -> UserPromptSubmit -> PostToolUse -> Stop -> SessionEnd Hooks (src/hooks/*.ts) - TypeScript -> ESM, built to plugin/scripts/*-hook.js Worker Service (src/services/worker-service.ts) - Express API on port 37777, Bun-managed, handles AI processing asynchronously Database (src/services/sqlite/) - SQLite3 at ~/.ultrabrain/ultrabrain.db Search Skill…

The file

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No need to edit the changelog ever, it's generated automatically.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

UltraBrain: AI Development Instructions

UltraBrain is a Claude Code plugin providing persistent semantic memory across sessions. It captures tool usage, compresses observations using the Claude Agent SDK, embeds them into LanceDB for vector search, and injects relevant context into future sessions.

Architecture

5 Lifecycle Hooks: SessionStart -> UserPromptSubmit -> PostToolUse -> Stop -> SessionEnd

Hooks (src/hooks/*.ts) - TypeScript -> ESM, built to plugin/scripts/*-hook.js

Worker Service (src/services/worker-service.ts) - Express API on port 37777, Bun-managed, handles AI processing asynchronously

Database (src/services/sqlite/) - SQLite3 at ~/.ultrabrain/ultrabrain.db

Search Skill (plugin/skills/mem-search/SKILL.md) - HTTP API for searching past work, auto-invoked when users ask about history

Vector Search (src/services/sync/LanceSync.ts) - LanceDB vector embeddings for semantic search (native Rust, in-process)

Embeddings (src/services/sync/EmbeddingService.ts) - @xenova/transformers with all-MiniLM-L6-v2 (384-dim, in-process ONNX)

Viewer UI (src/ui/viewer/) - React interface at http://localhost:37777, built to plugin/ui/viewer.html

Privacy Tags

  • <private>content</private> - User-level privacy control (manual, prevents storage)

Implementation: Tag stripping happens at hook layer (edge processing) before data reaches worker/database. See src/utils/tag-stripping.ts for shared utilities.

Build Commands

npm run build-and-sync        # Build, sync to marketplace, restart worker

Configuration

Settings are managed in ~/.ultrabrain/settings.json. The file is auto-created with defaults on first run.

File Locations

  • Source: <project-root>/src/
  • Built Plugin: <project-root>/plugin/
  • Database: ~/.ultrabrain/ultrabrain.db
  • Vector DB: ~/.ultrabrain/vector-db/ (LanceDB)

Exit Code Strategy

Hooks use specific exit codes per Claude Code's hook contract:

  • Exit 0: Success or graceful shutdown
  • Exit 1: Non-blocking error (stderr shown to user, continues)
  • Exit 2: Blocking error (stderr fed to Claude for processing)

Requirements

  • Bun (all platforms - auto-installed if missing)
  • Node.js >= 18

Important

No need to edit the changelog ever, it's generated automatically.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free