npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@teambrain/cli

v0.3.0

Published

tb — git-native, human-governed shared memory for AI coding agents (CLI, daemon, MCP server)

Downloads

602

Readme

@teambrain/cli

tb — git-native, cross-vendor shared memory for AI coding agents.

TeamBrain gives Claude Code, Cursor, and other MCP-capable agents one shared, human-governed memory: markdown files in your repo, served over MCP by a local daemon, with new memories proposed as pull requests — never written silently.

npm install -g @teambrain/cli

Quick start

tb init                  # import CLAUDE.md / .cursorrules / ADRs → a PR branch
tb install claude-code   # register the MCP server + capture wiring (also: cursor)
tb serve                 # run the local daemon (index + watcher + MCP backend)
tb doctor                # verify daemon, index, and capture health

Everyday commands

tb audit --last-session   # see exactly what was recorded, post-redaction
tb propose --class learning --title "..." --body "..."   # queue a candidate
tb retire <id> "reason"   # open a PR retiring a memory
tb reindex                # rebuild the local index (recovery path)
tb lint .teambrain        # validate memories (schema, size, injection heuristics)
tb distill --dry-run      # (CI) cluster sessions → memory-proposals PR
tb digest --dry-run       # (CI) people-free weekly digest

Run tb --help or tb <command> --help for grouped help, exit codes, and examples.

How it works

  • Git is the source of truth. Memories are markdown + YAML front-matter in .teambrain/; approval is a pull request, history is git log.
  • A local daemon serves them over MCP (memory_context, memory_search, memory_propose, memory_feedback) with hybrid lexical + vector retrieval.
  • Capture is metadata-only and redacted on-device — never raw prompts, file contents, or diffs. tb audit shows you exactly what was stored.
  • Nothing writes to the brain without a human merge. Automation proposes; people approve.

Part of TeamBrain

This is the command-line entrypoint. The implementation lives in @teambrain/core, @teambrain/index, @teambrain/mcp, @teambrain/hooks, @teambrain/redact, and @teambrain/distill.

Full docs, format spec, and threat model: github.com/donatienmigue/TeamBrain

Apache-2.0