Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Global Brain: Cross-Project Claude Code Memory

    1

    Give Claude Code one memory across all your projects. A local SQLite brain captures commits, topics and files from your transcripts and loads a small digest into every session.

    Free

    5.0 (1 review)
    Global Brain: Cross-Project Claude Code Memory

    Global Brain: Cross-Project Claude Code Memory

    Example session with this skill installed

    /global-brain what did we decide about pagination?

    • Read your context and instructions
    • Compiled the global brain

    Real CLI output from a test install, with sample entries:

    1 result — "pagination":
    
    #1 [api · decision · 2026-11-04] 🌐 Use cursor pagination
        Offset pagination timed out on large tables; all list endpoints use cursors.
        (imp 70 · manual)
    

    The agent then answers in prose and cites the entry. The digest loaded into new sessions:

    
    ## 📌 Cross-project / pinned
    - [api · decision · 2026-11-04] Use cursor pagination — Offset pagination timed out on large tables; all list endpoints use cursors.
    
    ## web
    - [web · preference · 2026-11-04] Dates in UTC — Store dates in UTC and format them only in the UI.
    

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Claude Code starts each project without what you learned in the others. Global Brain keeps that knowledge in one local database and loads a size-limited digest into every session.

    • Automatic capture: reads Claude Code transcripts and extracts commits, topics, files and goals.
    • Saved on request: store decisions, preferences and gotchas with remember, and search them with query.
    • Bounded: token and per-project limits keep the digest small.
    • Local: memory stays in ~/.claude/global-brain/brain.db.
    • Secret-aware: values that look like API keys, tokens or passwords are masked as [REDACTED] before they are stored or loaded into the digest.
    • Clean removal: global-brain uninstall removes the hooks, restores your previous status line and removes the CLAUDE.md import. Your memory is kept unless you pass --purge.
    • Open source: MIT licensed, with zero runtime dependencies.

    What setup changes: this skill installs the @kxrk0/global-brain npm package after asking you. It adds two hooks, wraps your status line (the previous one is saved and restored on uninstall), and adds one import line to CLAUDE.md. It also checks npm for updates in the background, which you can turn off.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Works only with Claude Code and requires Node 22.13+. Automatic capture is heuristic (no LLM) and can miss details, so use remember for anything important. Secret masking is pattern-based: it catches common key and token formats and password=-style values, but do not paste secrets into prompts on purpose. Background version checks run at most every 15 minutes unless disabled with GLOBAL_BRAIN_NO_UPDATE_CHECK=1.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    Trust & safety

    Security scan

    Security scan passed 12 days ago

    • Free with an Agensi account

    Software
    Claude CodeNode.js 22.13+npm

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files

    File Scopes

    ~/.claude/global-brain/**
    ~/.claude/skills/global-brain/**
    ~/.claude/settings.json
    ~/.claude/CLAUDE.md
    ~/.claude/global-brain.md
    ~/.claude/projects/**

    Shell runs the global-brain CLI and the npm install, after user approval. File access covers ~/.claude/global-brain, ~/.claude/skills/global-brain, settings.json, CLAUDE.md, global-brain.md and the transcripts in ~/.claude/projects (read only). Network use is the npm install and a version check against registry.npmjs.org. The database stays on your machine; the digest is loaded into Claude Code sessions like any CLAUDE.md content, with values that look like secrets masked first. `global-brain uninstall` reverts the settings.json and CLAUDE.md changes.

    Listed12 days ago

    What's inside

    Frequently Asked Questions

    Claude Code's memory files are tied to one project, so a decision or gotcha you worked out in one repo is not there when you open another. Global Brain stores those decisions and conventions in one local database and loads a bounded digest into every session, in every project.

    This skill is built for Claude Code and requires Node.js 22.13 or newer. The database stays on your machine in a local SQLite file and is not uploaded to a memory service. Values in your transcripts that look like API keys, tokens or passwords are masked before they are stored. The digest is imported through CLAUDE.md, so like the rest of your Claude Code context, it is sent to the model during your sessions.

    Run /global-brain and the skill offers to install the @kxrk0/global-brain npm package, explaining every change first. After install it syncs your existing transcripts automatically and keeps syncing at the start and end of each session. Use 'remember' to save specific global preferences, and 'global-brain doctor' to check the setup.

    Yes, while 'sync' automates history ingestion, you can use the 'remember' command to explicitly save specific rules, and use entry IDs to 'pin' important facts or 'forget' outdated architectural decisions.

    Yes. This listing is free, and the CLI is MIT licensed with its source on GitHub. Updates are installed through npm.

    Unlike a prompt you have to maintain by hand, Global Brain updates its digest from your transcripts and loads it through CLAUDE.md, so new sessions in any project start with your saved decisions and preferences.

    Run 'global-brain uninstall', then 'npm uninstall -g @kxrk0/global-brain'. Uninstall removes the hooks, restores the status line you had before, removes the CLAUDE.md import, the skill and the engine, and leaves your other settings alone. Your saved memory is kept; add --purge only if you want it deleted permanently. Use --dry-run to preview the changes.

    New in Agents & Orchestration

    Free