Agent Teams AI is an open-source multi-agent orchestration harness developed by 777genius. It is designed to manage, coordinate, and execute developer workflows across collaborative teams of autonomous AI agents. The harness structure centers on an agent-teams-controller module that provisions team instances and oversees inter-agent coordination for complex software development tasks. In practical use, Agent Teams AI coordinates lead agents and sub-agents to handle codebase operations, issue resolution, and code modifications. The framework provides a provisioning service (TeamProvisioningService) that maintains live lead replies, handles message deduplication across sessions, and tracks task progress through a task store and dashboard views. The platform supports remote LLM execution alongside experimental local model launches, allowing developers to allocate different tasks to suitable model backends. What distinguishes Agent Teams AI is its team-based lifecycle architecture. Rather than relying on a monolithic prompt-loop agent, it implements structured task state management with canonical UUID-based task comments, path security validation for user-selected project paths, and dedicated controller components for process lifecycle management. The project is open source on GitHub and built primarily within the Node.js/TypeScript ecosystem with Docker containerization support for isolated agent execution environments.
Team Controller Architecture — Coordinates multi-agent provisioning and communication via dedicated controller modules. - Task State & Comment Store — Tracks task progression and UUID-based task comments for context sharing across agent runs. - Local & Remote Model Support — Configurable execution pipelines that support both cloud-based providers and experimental local model launches. - Message Deduplication & Provisioning — Manages live lead agent sessions with built-in message deduplication to avoid redundant context processing. - Security-Scoped File Path Validation — Enforces path validation safeguards on user-selected directory contexts during agent execution. - Interactive Dashboard & Activity Views — Provides visibility into team status, active processes, and task completion metrics. - Containerized Deployment Support — Includes Docker configurations for running isolated team environments and controlling background worker processes.
Use cases
Use Case: Coordinated Multi-Agent Code Refactoring A developer decomposes a broad refactoring effort across an agent team, assigning a lead agent to analyze repository structure while sub-agents execute scoped file edits and report progress back to the controller.
Use Case: Local Model Agent Workflows A team with strict privacy requirements runs agent teams against local model deployments using the harness's local model launch capabilities, keeping code context within on-prem infrastructure.
Use Case: Task-Driven Issue Resolution An engineering pipeline queues tasks in the central task store, where agents fetch canonical task comments, plan implementation steps, apply changes, and record progress updates automatically.
Who it is for
Agent Teams AI is intended for software engineers and AI system architects looking to build and run multi-agent developer workflows with structured lead-and-worker delegation. It fits teams wanting fine-grained control over process provisioning and local model execution, but is less suited for developers seeking a turnkey, single-binary CLI agent for simple one-off file edits.
Install guide
Installation Clone the repository and install dependencies using Node.js/npm (standard repository setup): bash git clone https://github.com/777genius/agent-teams-ai.git cd agent-teams-ai npm install Alternatively, build and run using Docker: bash docker compose -f docker/docker-compose.yml up -d
First Run Configure your environment variables and model endpoints in your .env file: bash cp .env.example .env # Set your API keys or local model server endpoints export OPENAI_API_KEY="your-api-key" export LOCAL_MODEL_ENDPOINT="http://localhost:11434" Start the agent controller service: bash npm run dev
Example Session Launch a team-directed coding task through the CLI controller entrypoint: bash # Initialize an agent team session on a target project path node bin/agent-teams start --path ./my-project --task "Refactor auth middleware and update test suite"
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…