openteams-lab/openteams

Plan, Build, and Ship — with a team of AI agents instead of one

What it solves

Developers often use multiple AI coding agents (like Claude Code, Codex, or Gemini CLI) in separate terminal windows, leading to fragmented context, redundant communication, and difficulty tracking changes. openteams provides a unified, local-first workspace where these agents can collaborate in a shared session, allowing developers to manage them as a cohesive team rather than isolated tools.

How it works

It acts as a management layer over existing coding agents. Instead of replacing them, it integrates them into a single interface. Key mechanisms include:

  • Shared Sessions: A common room where multiple agents can communicate and hand off work while maintaining the same project context.
  • Workflow Mode: A structured approach to complex tasks that breaks them into steps with dependencies, allowing for granular review and retries of specific steps.
  • Isolated Workspaces: Integration with Git worktrees to ensure that parallel tasks handled by different agents do not overwrite each other's changes.
  • Issue Management: A developer-controlled list of tasks that links specific work items to the agent sessions executing them.

Who it’s for

  • Indie developers who use multiple AI agents to build software faster.
  • Technical leads who require a reviewable and reproducible record of agent-driven development.

Highlights

  • Multi-agent support: Compatible with 16+ coding agents including Claude Code, Gemini CLI, and a bundled openteams-cli.
  • Local-first design: A desktop app (built with Tauri and Rust) that keeps runtime records and workspace execution local.
  • Build Statistics: Tracks token usage and costs alongside the actual features delivered or bugs fixed.
  • Git Worktree Integration: Prevents interference between parallel agent tasks by using separate worktrees for different sessions.
  • Developer-led Roadmap: Ensures agents perform the work without being allowed to rewrite the project plan.

Related

  • Project
    xintaofei/codeg

    A multi-agent coding workspace that aggregates various AI coding agents into one searchable interface, enabling multi-agent collaboration and unattended task execution via Git worktrees.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    openchamber/openchamber

    An open-source workspace for running, supervising, and reviewing AI coding agent work across desktop, browser, editor, and mobile devices.

  • Project
    solo-agent/solo

    An open-source, local-first workspace that coordinates multiple AI coding agents through shared channels, task boards, and long-term memory.

  • Project
    Kc1t/alethe-agents

    A local-first desktop workspace for running multiple AI coding agents and shells side-by-side with persistent sessions and shared MCP server management.