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

@takemo101/asem

v0.0.2

Published

Local agent Session manager CLI

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

takemo101takemo101

Keywords

Readme

@takemo101/asem

asem is a local agent Session manager for AI-assisted development. It helps a human or parent agent create child Sessions, exchange Messages, collect Reports, and inspect local work from a CLI, TUI Cockpit, or stdio MCP server.

Manual: https://takemo101.github.io/asem/
Repository: https://github.com/takemo101/asem

Install

Recommended with Bun:

bun install -g @takemo101/asem

npm also works when bun is available on your PATH:

npm install -g @takemo101/asem

The package installs the asem binary. It is built for Bun-based execution, so install Bun before running asem.

Verify the installed version:

asem --version

Quickstart

cd /path/to/your/repo
asem init --interactive
asem doctor
asem session create reviewer-1 --profile reviewer --prompt "Review the current diff"
asem message list
asem tui

What it provides

  • Local Sessions: create and inspect child agent Sessions in a Workspace and Worktree Root.
  • Messages and Reports: keep durable local communication history between parent and child Sessions.
  • Multiplexer Templates: launch through tmux, zellij, herdr, rmux, or project-local Templates.
  • Agent Profiles: shape child prompts with explicit Profiles such as reviewer, worker, and planner.
  • TUI Cockpit: inspect Sessions and local activity from a keyboard-first terminal surface.
  • Stdio MCP server: expose primitive Session and Message operations to compatible AI clients.
  • Integration Target setup: register MCP or install Skill guidance for supported external AI clients.

asem is intentionally small. It is not a task board, scheduler, hosted service, workflow engine, or result evaluator.

Built-in Agent Templates

asem ships with built-in Agent Templates for common agent CLIs:

  • claude, codex, pi, gemini — positional prompt seeds the interactive session.
  • agy — uses --prompt-interactive for the initial prompt.
  • opencode — uses --prompt for the initial interactive TUI prompt.
  • kimi — starts the interactive TUI bare and pastes the prompt after a boot delay (paste_prompt: true); it uses -m for model selection.

Use asem doctor to check that the selected Agent CLI is installed and reachable.

More information

See the manual for concepts, CLI usage, TUI behavior, Agent Profiles, MCP setup, Skills, and configuration:

https://takemo101.github.io/asem/