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

@codaph/codaph

v0.1.18

Published

CLI/TUI for coding-agent activity with shared Mubit memory. Supports Claude Code, Codex, and Gemini CLI.

Readme

Codaph

Replay how your codebase was built. Codaph captures agent prompts, reasoning, and file diffs from Claude Code, Codex, and Gemini CLI into a shared Mubit memory that your whole team can search semantically.

Unlike git-local session logs, Codaph gives your team shared semantic memory across agents and contributors.

[!WARNING] Codaph is in beta. Be mindful.

Get Started

npm i -g @codaph/codaph
codaph enable

That's it. codaph enable auto-detects your agents, installs hooks, and optionally connects to Mubit cloud memory. Works without a Mubit key too (local-only mode).

Then explore your agent activity:

codaph tui

Why Codaph + Mubit

When multiple engineers work with coding agents in parallel, the reasoning behind changes gets lost. Onboarding a new engineer or agent means a cold start every time.

Codaph captures the full story (prompts, thoughts, diffs) locally, and Mubit shares it as searchable semantic memory across your team. Ask "what changed in auth?" and get answers ranked by relevance from everyone's agent sessions.

Agent Support

  • [x] Claude Code
  • [x] Codex (OpenAI)
  • [x] Gemini CLI (Google)
  • [ ] Cursor (planned)
  • [ ] OpenCode (planned)
  • [ ] GitHub Copilot CLI (planned)

Roadmap

  • [ ] Rust rewrite for performance
  • [ ] Mubit state subscription for auto exec / scripting
  • [ ] Dependencies map and upgrade sync
  • [ ] Plugin system for coding agents

Installation

npm (recommended)

npm i -g @codaph/codaph

From source

git clone https://github.com/mubit-ai/codaph.git
cd codaph
bun install
bun run build

Usage

# one-command setup (recommended)
codaph enable

# open terminal UI
codaph tui

# daily sync
codaph pull

# backfill agent history to Mubit
codaph push

# check sync status
codaph status

Advanced Setup

For granular control, use the individual setup commands:

# global key setup
codaph setup --mubit-api-key <your-mubit-key>

# optional: OpenAI-assisted query/chat
codaph setup --openai-api-key <your-openai-key>

# per-repo init with provider selection
codaph init

You can also set MUBIT_API_KEY, OPENAI_API_KEY, and OPENAI_MODEL as environment variables.

codaph init also writes a reusable Claude Code MCP template at .codaph/mcp/claude-code.json. Use codaph mcp setup claude to print (or run with --run) the recommended claude mcp add ... command.

Optional query example (OpenAI-assisted if OPENAI_API_KEY is set, otherwise Mubit response):

codaph mubit query "what changed in auth?"
codaph mubit query "what is the current direction of this repo?" --rank-by freshness
codaph mubit query "what changed in auth?" --session <session-id>
codaph mubit activity --limit 20 --exclude-derived --projection compact

If you are running from source, use bun run cli instead of codaph.

bun run cli init --cwd /absolute/project/path
bun run cli sync --cwd /absolute/project/path
bun run cli tui --cwd /absolute/project/path

MCP (Claude Code)

Codaph ships a local MCP server over stdio:

codaph mcp

Recommended setup (personal use):

codaph mcp setup claude --scope user --run

This uses Claude Code user scope (~/.claude.json) so one Codaph MCP config works across repos.

Project scope (.mcp.json) is also supported when you want a shared/team config. codaph init writes a copy/merge template at .codaph/mcp/claude-code.json.

See MCP Setup (Claude Code) for claude mcp add commands, JSON examples, and troubleshooting.

Documentation

Start with Quickstart for Mubit API key setup, optional OpenAI-assisted query/chat setup, and the recommended first-run flow.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests and documentation as appropriate.

License

Dual-licensed under either of the following, at your option:

  • MIT
  • Apache License 2.0

See LICENSE for the full text of both licenses.