OpenTeam Download for macOS

A local-first AI work team

Not another chatbot. OpenTeam organizes different models, roles, and agents into a team that can challenge, review, verify, and deliver real project work together.

Download for macOS Explore product
  • MIT License
  • Node 20.19+ / 22.12+
  • pnpm 10.x
Actual OpenTeam desktop home screen showing Team templates and local task setup
Actual OpenTeam UI captured from the latest main branch.
Why OpenTeam?

AI agents are moving from single bots to working teams.

Many products still treat a team as multiple roles taking turns in a chat. OpenTeam focuses on real project work: constraints, handoffs, reviews, QA, and local workspace context.

Local-first

Project files, context, and team memory stay on your machine first.

Free and open-source

MIT License, no seat pricing, and no platform lock-in.

Multi-model collaboration

Different agents can use different providers and models for the job.

Cross-checking

Planning, research, implementation, review, and QA can constrain each other.

Self-evolving

Preserve project rules, user preferences, workflows, and lessons learned.

Use cases

Simple AI panels for concrete disputes and decisions.

These pages are for people searching for a practical way to rehearse arguments, handle customer disputes, or challenge business decisions before they act.

Legal and dispute preparation

AI legal argument simulation

Use several AI roles to rehearse a court-style debate, find weak points, and prepare stronger arguments. Not legal advice.

Open page
Customer complaint handling

AI complaint and after-sales panel

Bring chat records, platform tickets, contracts, and customer claims. Get a one-page risk and response plan.

Open page
Business decision review

AI business decision challenge

Let AI roles argue both sides of a launch, pricing, partnership, hiring, or product decision before you commit.

Open page
Workflow

Make the team argue with the work, not just talk around it.

OpenTeam keeps the roles and evidence visible so a room can move from intent to delivery without losing the reasoning chain.

  1. 01

    Plan

    Start with a Team, a Workspace, and acceptance criteria for the room.

  2. 02

    Research

    Agents can ask, challenge, and supplement each other with @mention.

  3. 03

    Implement

    Specialists work through the real project context instead of a detached prompt.

  4. 04

    Review and QA

    Reviewers demand tests, logs, screenshots, and concrete evidence before closure.

Configuration

Teams are configured, not improvised.

Settings expose the same objects the product is built around: Provider, Agent, Team, Team Architect, and Skills.

Provider CLI path, API Key, Base URL, and default model.
Agent Role name, Provider, model override, System Prompt, and tags.
Team Description, workflow prompt, collaboration rules, and acceptance criteria.
Skills Built-in and workspace-discovered capabilities available to the room.
Actual OpenTeam settings screen showing Team configuration, member roles, tools, and skills
Actual Settings screen captured after loading Team data.
Roadmap

Team Memory

Preserve project rules, user preferences, and decisions.

Team Playbooks

Reusable workflows for engineering, research, writing, and distribution.

Evidence Trail

Link conclusions to files, commands, sources, and verification results.

Windows desktop

Packaging, signing, and auto-update for Windows users.

Run the AI team from your own machine.

The desktop app runs frontend and backend capabilities inside Electron. It does not expose HTTP service ports to end users, and upgrades do not overwrite local SQLite, workspaces, or Provider configuration.

Download for macOS View source