Open Multi-Agent: TypeScript Multi-Agent Orchestration Framework

What is Open Multi-Agent?

Open Multi-Agent is an open-source TypeScript framework for multi-agent AI orchestration, designed for AI engineers and TypeScript developers. It enables you to build goal-driven task DAGs, parallel LLM calls, and mixed-model teams.

Core Capabilities

• Runtime Task DAGs: A coordinator agent decomposes a goal into a task DAG at runtime, runs independent nodes in parallel, and synthesizes a typed result.
• Mixed-Model Teams: Mix any model in one agent team—use a strong model where it earns its cost and a cheap one everywhere else, in the same team, in one run.
• Local & Private Deployment: Runs against a local Ollama endpoint just like a cloud provider, allowing the whole team, coordinator included, to run on a small local model at zero API cost.
• Vercel AI SDK Integration: Acts as a coordination layer above a Vercel AI SDK app, keeping the AI SDK for streaming and model calls.
• Flexible Configuration: Give the planner its own model, adapter, or extra instructions without touching the worker agents.

Use Cases

• Turn a goal into a task DAG at runtime
• Adaptive customer support with coordinator and specialists
• Add multi-agent orchestration to a Vercel AI SDK app
• Run a local, private multi-agent team with Ollama
• Mix any model in one agent team

Technical Details

• MIT licensed, open-source.
• Public API available.
• Self-hosted.
• Medium learning curve.
• Monetization includes free and freemium.
• Three runtime dependencies.
• Supports cloud, local, or air-gapped models on your credentials.

Considerations

• Bash stays unsandboxed once granted, and every tool result is sent to your model provider—so grant read/exec access on purpose.
• Pricing model is unknown.