OpenViSTAI · Agents · Blockchain · Crypto
Menu
Coding Agents

Codeman

Codeman is a self-hosted web application for running and monitoring AI coding agents in persistent tmux sessions, with live terminal streaming, scheduled jobs and background-agent visibility.

Independent OpenViST project profile, based on linked sources.

Codeman — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Codeman when you need a self-hosted control surface for persistent coding-agent sessions, especially for work that continues while you are disconnected or requires monitoring of background agents.

Who it is for

  • Developers already using supported coding-agent command-line tools.
  • Operators who want to supervise persistent agent sessions from a browser or another device.
  • Teams or individuals monitoring background agents and scheduled coding work.

Documented uses

  • Start supported coding-agent CLIs and keep their terminal sessions persistent.
  • Stream agent terminals to a browser dashboard and review session activity.
  • Re-prompt idle agents and resume them after usage limits reset.
  • Schedule agent jobs and watch subagent or teammate activity.
Before you choose

Requirements & limits

The project is self-hosted and MIT-licensed. The README documents installation on macOS and Linux, Windows through WSL, and session modes including Docker and SSH.

  • Codeman operates supported agent CLIs; it is not itself a coding model.
  • The documented stack includes Node.js 22 or later, TypeScript 5.9, Fastify 5.x and tmux.
  • The installer offers local-only, network and Tailscale access choices; the README advises setting a password before exposing access through a tunnel.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Codeman and open its local dashboard

Install Codeman on macOS or Linux and reach the dashboard on the host machine.

Before you start

  • macOS or Linux; Windows users are directed to use WSL.
  • The installer may request consent for missing packages, a sudo password, or Tailscale login depending on the chosen setup.

Steps

  1. Run the command below.

    Documented command
    curl -fsSL https://getcodeman.com/install | bash
  2. Choose how the dashboard should be reached during installation.

  3. Run codeman web if needed, then open http://localhost:3000.

Expected outcome

The Codeman dashboard is available at localhost for starting a session.

Guide limitations

  • The installer installs Node.js, tmux and a build toolchain if missing.
  • The documented installation path is macOS and Linux, with Windows via WSL.
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
CodemanStart supported coding-agent CLIs and keep their terminal sessions persistent.Docker, Self-hosted, WebThe project is self-hosted and MIT-licensed. The README documents installation on macOS and Linux, Windows through WSL, and session modes including Docker and SSH.
LlmcodeInspect a project's directory structure with `/tree`.CLIThe documented setup requires an API key and supports an API base URL and model setting. The project is open source under Apache-2.0.
Klaat CodeOpen a project directory for terminal-based coding assistance.CLI, ServerThe README provides a global npm installation command and documents browser sign-in with a KlaatAI account. It also identifies the repository as open source under Apache 2.0.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Ark0N/Codeman · Official homepage title · retained in its source language