open-multi-agent

open-multi-agent is an agent framework - From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.

Overview

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration. Three runtime dependencies.

'open-multi-agent' is a multi-agent orchestration framework for TypeScript backends. Give it a goal; a coordinator agent decomposes it into a task DAG, parallelizes independents, and synthesizes the result. Three runtime dependencies, drops into any Node.js backend.

Graph-first frameworks make you enumerate every node and edge up front. 'open-multi-agent' is goal-first: you describe the outcome and the coordinator builds the task DAG at runtime, so the orchestration adapts to the goal instead of being hand-wired for one.

Quick Start · Three Ways to Run · Features · Orchestration Controls · Ecosystem · Examples · How Is This Different? · Architecture · Supported Providers · Production Checklist · Documentation · Contributing

Migrating from '@jackchen_me/open-multi-agent'? That package is deprecated; install '@open-multi-agent/core' instead.

Local models via Ollama need no API key, see 'providers/ollama'. For hosted providers ('OPENAI_API_KEY', 'GEMINI_API_KEY', etc.), see Supported Providers.

For answers that need scrutiny, 'runConsensus()' runs a proposer→judge verification loop (with an opt-in per-task 'verify' hook). See Consensus.

Production controls (context strategies, task retry with backoff, loop detection, tool output truncation/compression) are covered in the Production Checklist.

Fine-grained control over a 'runTeam' run. All optional; defaults keep behavior unchanged.

open-multi-agent is open-source, written primarily in TypeScript, with 6,338 GitHub stars under the MIT license. The latest release is v1.6.0 (2026-06-06).

Key capabilities

From the project's documentation:

• basics/team-collaboration: runTeam() coordinator pattern.
• patterns/structured-output: any agent returns Zod-validated JSON.
• patterns/agent-handoff: synchronous sub-agent delegation via delegate_to_agent.
• Documentation. Guides, tutorials, and API docs.
• @apollo-mg (context compaction fix, sampling parameters)
• @Xin-Mai (output schema validation)

How it fits a local-AI stack

open-multi-agent runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

• Agno
• AutoGPT
• CrewAI
• Genkit

Sources

• Source code & docs: open-multi-agent/open-multi-agent
• Official website: https://open-multi-agent.com

Stats from GitHub, 2026-06-08.