Back: Catalog

Open Multi Agent

Open Multi-Agent is a self-hosted TypeScript agent runtime environment. It waits for permanent approvals on critical vehicle calls and leaves offline verifiable records for each run. It does not host telemetry, and the cloud works in your own infrastructure with local (Olma, vLLM, llama-server) or OpenAI compatible models.

OP

Open Multi Agent

80

open-multi-agent · AI Agent Frameworks

STARS7.0K
FORKS2.4K
COMMITS—
CONTRIBUTORS0
VERSIONv1.9.0
UPDATEDyesterday
TypeScriptMulti-AgentOrchestrationDAGMIT

Common commercial products in this category: OpenAI Assistants API, Microsoft Copilot Studio, Amazon Bedrock Agents

What can it do?
  • You run a single agent, run an open pipe, or plan a team based on a target.
  • You set up durable and hash-based flows that expect human approval on critical vehicle calls
  • You manage agent operations by adding @open-multi-agent/core package to TypeScript projects
User reviews
  • • NeutralGitHub Issue

    [Tracker] Propose a cookbook example (selective intake)

    “> **Selective intake (updated 2026-09-03).** > Cookbook coverage has reached a plateau. Read the bar below before commenting. ## Already covered The `examples/cookbook/` directory has 11 examples: - Legal: `contract-review-dag.ts` - Medical: `rare-disease-information-triage.ts`…”

  • • NeutralGitHub Issue

    [Feature] OpenAI-compatible provider integrations (DeepSeek, Mistral, Groq, Zhipu, MiniMax, Qwen, Moonshot, Doubao)

    “These providers offer OpenAI-compatible APIs and should work via existing `openai` provider with custom `baseURL`. Each one needs: 1. **Verify** tool-calling works correctly 2. **Add a working example** to `examples/` 3. **Document** in README under Supported Models | Provider |…”

Website GitHub

My note

Alternative pages

OpenAI Assistants API alternativesMicrosoft Copilot Studio alternativesAmazon Bedrock Agents alternatives

More in: AI Agent Frameworks