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

@ai-devkit/agent-manager

v0.28.0

Published

Standalone agent detection and management utilities for AI DevKit

Readme

@ai-devkit/agent-manager

Detect, inspect, and send prompts to running AI coding agent sessions.

This package powers the ai-devkit agent commands. Use it when you need the lower-level agent session management utilities that AI DevKit uses to find active Claude Code, Codex, Gemini CLI, and other supported coding-agent sessions.

What It Provides

  • Session detection — Find running agent sessions across supported providers
  • Session details — Inspect agent metadata, working directory, and status
  • Prompt sending — Send follow-up instructions to an existing session
  • Provider adapters — Shared adapter layer for agent-specific behavior
  • Terminal control — Discover, focus, and type into the terminal pane that hosts a running agent. Supported emulators: tmux, WezTerm, iTerm2, and macOS Terminal.app. Resolution is automatic from the agent PID's TTY.

Typical Use

Most users should use the CLI:

ai-devkit agent list
ai-devkit agent send "run the tests and report back" --id <agent-name> --wait
npm test 2>&1 | ai-devkit agent send --id <agent-name> --stdin

Claude Code can also be registered as a durable agent. Registration does not launch Claude; each send starts one synchronous process and later sends resume the same Claude session:

ai-devkit agent start --type claude --mode durable --name reviewer --cwd /path/to/project
ai-devkit agent send "review the current diff" --id reviewer

Durable mode inherits Claude Code's settings, permissions, hooks, MCP servers, and tool side effects for that working directory. AI DevKit adds no permission bypass or automatic retry, and prompts are delivered over stdin rather than command-line arguments. --timeout is not supported for durable agents in this first release.

Durable durable-agent state is stored in ~/.ai-devkit/agents.db. This feature was not released with JSON persistence, so there is no legacy import or dual-write.

For direct DurableAgentRepository consumers, dbPath selects the SQLite database. The lockTimeoutMs, incompleteLockGraceMs, and mutationLockStaleMs options are deprecated, accepted, and ignored because SQLite transactions replace the filesystem lock machinery.

Use this package directly only when building custom tooling around AI DevKit's agent detection and control surface.

Documentation

Full guides and workflow examples: ai-devkit.com/docs

License

MIT