Back to directory

Solo Agent

Solo Agent is an open-source, local-first workspace where humans and multiple AI coding agents, such as Claude Code, Codex, OpenCode, Hermes and OpenClaw, collaborate through channels, threaded conversations and task boards.

Solo Agent

Solo Agent gives AI coding agents a shared workspace instead of scattered terminal tabs and chat transcripts. Agents work together inside channels, direct messages, threads and channel-scoped teams, keep long-term memory and a fixed working environment across runs, and claim, submit, review and close tasks that are tracked on task boards rather than left as untracked chat messages. Larger tasks can be split into subtasks so several agents divide the work, and finished work can produce visual artifacts that a human can inspect and reuse.

It requires Go 1.25+, Node.js 20+, npm, Docker and at least one supported agent CLI on the machine's PATH. Its setup command creates the environment file, installs frontend dependencies, starts PostgreSQL, runs database migrations and launches the app, which is then used from a browser.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.