Mjolnir

One control plane for all your coding agents.

Mjolnir (mj) runs Claude Code, Codex, Kimi Code, Grok Build, and Muse Code sessions side by side, on your laptop, in containers, over SSH, or on EC2, and keeps them running after you close the terminal. You can move a session to another account, another harness, or another machine without starting over.

By default Mjolnir sends recent prompt and reply text, and help-search text, to TypeSafe's hosted Jev classifier through a public proxy, and [jev] enabled = false in config.toml stops all of it (details).

Documentation · Quickstart · Releases

Why Mjolnir

If you use one agent, in one terminal, on one machine, you don't need Mjolnir. It's for the point where that stops scaling: several subscriptions, several repositories, several machines, and work that should keep going when you walk away.

• Sessions that outlive your terminal. Each session runs beside a worker that owns its prompt queue and event journal. Detach, close the terminal, or restart the daemon; the agent keeps working and you reattach where you left off.
• Run anywhere. Use a local worktree, a Docker, Podman, or Apple container, any Linux host over SSH, or an EC2 instance provisioned from a launch template. Remote hosts need no resident daemon; Mjolnir uploads a worker on demand.
• Move work freely. Switch a session from your personal Codex account to your work account, from Codex to Claude Code, or from your workstation to EC2. Checkpoints are verified before anything is torn down.
• See every account's quota. Keep multiple named profiles per harness and watch remaining subscription quota and target capacity in one view.
• Shared project memory. Agents share synchronized project memory across sessions, harnesses, and targets, so what one session learns the next one knows.
• Adversarial review. Turn it on and an independent reviewer, on a different provider when one is available, checks each turn's work and reports actionable findings.
• Multi-repo projects. Bundle several repositories so they provision, checkpoint, move, and restore together.
• Terminal, web, and desktop. A full terminal dashboard, plus a privacy-first web viewer you can reach from your phone over Tailscale, and a desktop app. All three share the same live sessions.

Install

On Linux or macOS (use WSL2 on Windows):

curl -fsSL https://raw.githubusercontent.com/BrokkAi/mjolnir/master/install.sh | bash

Or with npm:

npm install -g @brokkai/mjolnir

Linux releases need glibc 2.28 or newer on x86-64 or ARM64. See the installation guide for Cargo, source builds, and desktop dependencies.

Quick start

From a project directory:

mj go

The first run asks you to pick a harness account and where the session should run. Each folder remembers its setup, and running mj go again returns you to your last conversation. Plain mj opens the full dashboard of workspaces, sessions, targets, and quota.

mj doctor checks prerequisites and tells you how to fix anything missing. The quickstart walks through a first session end to end.

Documentation

• What is Mjolnir?: architecture, goals, and supported harnesses and runtimes.
• Profiles and harnesses: accounts, login, credentials, and skills.
• Targets and bundles: local, container, SSH, and EC2 environments, multi-repository projects, and shared memory.
• Sessions and durability: adoption, move, resume, checkpoints, and recovery.
• Terminal and web and desktop: controls and remote access.
• Turn review, configuration, CLI reference, and security.

The documentation site source lives in docs/. Looking for the previous generation? See Mjolnir 1.x.

About

Mjolnir is free and open source, built by the engineers at Brokk because we wanted to use it. It is licensed under GPL-3.0-only.