README.md

May 12, 2026 · View on GitHub

Open Multi-Agent

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

English · 中文

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.

Package update: the official npm package is now @open-multi-agent/core. The previous package, @jackchen_me/open-multi-agent, remains supported during the migration window.

Your engineers describe the goal, not the graph.

Quick Start

Requires Node.js >= 18.

Use it in your project

npm install @open-multi-agent/core

import { OpenMultiAgent, type AgentConfig } from '@open-multi-agent/core'

const agents: AgentConfig[] = [
  { name: 'architect', model: 'claude-sonnet-4-6', systemPrompt: 'Design clean API contracts.', tools: ['file_write'] },
  { name: 'developer', model: 'claude-sonnet-4-6', systemPrompt: 'Implement runnable TypeScript.', tools: ['bash', 'file_read', 'file_write', 'file_edit'] },
  { name: 'reviewer', model: 'claude-sonnet-4-6', systemPrompt: 'Review correctness and security.', tools: ['file_read', 'grep'] },
]

const orchestrator = new OpenMultiAgent({
  defaultModel: 'claude-sonnet-4-6',
  onProgress: (event) => console.log(event.type, event.task ?? event.agent ?? ''),
})

const team = orchestrator.createTeam('api-team', { name: 'api-team', agents, sharedMemory: true })
const result = await orchestrator.runTeam(team, 'Create a REST API for a todo list in /tmp/todo-api/')

console.log(result.success, result.totalTokenUsage.output_tokens)

Run an example locally

git clone https://github.com/open-multi-agent/open-multi-agent && cd open-multi-agent
npm install
export ANTHROPIC_API_KEY=sk-...
npx tsx examples/basics/team-collaboration.ts

Three agents collaborate on a REST API while onProgress streams the coordinator's task DAG:

agent_start coordinator
task_start design-api
task_complete design-api
task_start implement-handlers
task_start scaffold-tests         // independent tasks run in parallel
task_complete scaffold-tests
task_complete implement-handlers
task_start review-code            // unblocked after implementation
task_complete review-code
agent_complete coordinator        // synthesizes final result
Success: true
Tokens: 12847 output tokens

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

Three Ways to Run

Mode	Method	When to use	Example
Single agent	`runAgent()`	One agent, one prompt	`basics/single-agent`
Auto-orchestrated team	`runTeam()`	Give a goal, let the coordinator plan and execute	`basics/team-collaboration`
Explicit pipeline	`runTasks()`	You define the task graph and assignments	`basics/task-pipeline`

Preview the coordinator's task DAG without executing agents:

const plan = await orchestrator.runTeam(team, goal, { planOnly: true })

For MapReduce-style fan-out without task dependencies, use AgentPool.runParallel() directly. See patterns/fan-out-aggregate.

For shell and CI, use the JSON-first oma binary. See docs/cli.md.

Features

Capability	What you get
Goal-driven coordinator	One `runTeam(team, goal)` call. The coordinator decomposes the goal into a task DAG, parallelizes independents, and synthesizes the result.
Mix providers in one team	10 built-in: Anthropic, OpenAI, Azure, Bedrock, Gemini, Grok, DeepSeek, MiniMax, Qiniu, Copilot. Ollama / vLLM / LM Studio / OpenRouter / Groq via OpenAI-compatible. (full setup)
Tools + MCP	6 built-in (`bash`, `file_*`, `grep`, `glob`), opt-in `delegate_to_agent`, custom tools via `defineTool()` + Zod, stdio MCP servers via `connectMCPTools()`. (tool config)
Streaming + structured output	Token-by-token streaming on every adapter; Zod-validated final answer with auto-retry on parse failure. (`structured-output`)
Observability	`onProgress` events, `onTrace` spans, post-run HTML dashboard rendering the executed task DAG. (observability guide)
Pluggable shared memory	Default in-process KV; swap in Redis / Postgres / your own backend by implementing `MemoryStore`. (shared memory)

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

Examples

examples/ is organized by category: basics, cookbook, patterns, providers, integrations, and production. See examples/README.md for the full index.

Real-world workflows (`cookbook/`)

End-to-end scenarios you can run today. Each one is a complete, opinionated workflow.

contract-review-dag: four-task DAG for contract review with parallel branches and step-level retry on failure.
meeting-summarizer: three specialised agents fan out on a transcript, an aggregator merges them into one Markdown report with action items and sentiment.
competitive-monitoring: three parallel source agents extract claims from feeds; an aggregator cross-checks them and flags contradictions.
translation-backtranslation: translate EN to target with one provider, back-translate with another, flag semantic drift.

Patterns and integrations

basics/team-collaboration: runTeam() coordinator pattern.
patterns/structured-output: any agent returns Zod-validated JSON.
patterns/fan-out-aggregate: MapReduce-style fan-out via AgentPool.runParallel().
patterns/agent-handoff: synchronous sub-agent delegation via delegate_to_agent.
integrations/trace-observability: onTrace spans for LLM calls, tools, and tasks.
integrations/mcp-github: expose an MCP server's tools to an agent via connectMCPTools().
integrations/with-vercel-ai-sdk: Next.js app combining OMA runTeam() with AI SDK useChat streaming.
Provider examples: scripts under examples/providers/ covering hosted providers, OpenAI-compatible endpoints, and local models.

Run any script with npx tsx examples/<path>.ts.

How is this different from X?

A quick router. Mechanism breakdown follows.

If you need	Pick
Fixed production topology with mature checkpointing	LangGraph JS
Explicit Supervisor + hand-wired workflows	Mastra
Python stack with mature multi-agent ecosystem	CrewAI
AI app toolkit with broad model-provider support	Vercel AI SDK
TypeScript, goal to result with auto task decomposition	open-multi-agent

vs. LangGraph JS. LangGraph compiles a declarative graph (nodes, edges, conditional routing) into an invokable. open-multi-agent runs a Coordinator that decomposes the goal into a task DAG at runtime, then auto-parallelizes independents. Same end (orchestrated execution), opposite directions: LangGraph is graph-first, OMA is goal-first.

vs. Mastra. Both are TypeScript-native. Mastra's Supervisor pattern requires you to wire agents and workflows by hand; OMA's Coordinator does the wiring at runtime from the goal string. If the workflow is known up front, Mastra's explicitness pays off. If you'd rather not enumerate every step, OMA's runTeam(team, goal) is one call.

vs. CrewAI. CrewAI is the mature multi-agent option in Python. OMA targets TypeScript backends with three runtime dependencies and direct Node.js embedding. Roughly comparable orchestration surface; the choice is the language stack.

vs. Vercel AI SDK. AI SDK provides the LLM-call layer — provider abstraction, streaming, tool calls, and structured outputs. It does not orchestrate goal-driven multi-agent teams. The two are complementary: AI SDK for app surfaces and single-agent calls, OMA when you need a team.

Ecosystem

open-multi-agent launched 2026-04-01 under MIT. Known users and integrations to date:

In production

temodar-agent (~60 stars). WordPress security analysis platform by Ali Sünbül. Uses our built-in tools (bash, file_*, grep) directly inside a Docker runtime. Confirmed production use.
Cybersecurity SOC (home lab). A private setup running Qwen 2.5 + DeepSeek Coder entirely offline via Ollama, building an autonomous SOC pipeline on Wazuh + Proxmox. Early user, not yet public.

Using open-multi-agent in production or a side project? Open a discussion and we will list it here.

Integrations

Engram — "Git for AI memory." Syncs knowledge across agents instantly and flags conflicts. (repo)
@agentsonar/oma — Sidecar detecting cross-run delegation cycles, repetition, and rate bursts.

Built an integration? Open a discussion to get listed.

Provider community offers

Limited-time provider offers for open-multi-agent users. Listings are not paid endorsements.

MiniMax — Use MiniMax M2.7 in OMA's TypeScript multi-agent workflows. OMA users get 12% off the MiniMax Token Plan until 2026-06-30. See the MiniMax setup guide.

Featured partner

For products and platforms with a deep open-multi-agent integration. See the Featured partner program for terms and how to apply.

Architecture

┌─────────────────────────────────────────────────────────────────┐
│  OpenMultiAgent (Orchestrator)                                  │
│                                                                 │
│  createTeam()  runTeam()  runTasks()  runAgent()  getStatus()   │
└──────────────────────┬──────────────────────────────────────────┘
                       │
            ┌──────────▼──────────┐
            │  Team               │
            │  - AgentConfig[]    │
            │  - MessageBus       │
            │  - TaskQueue        │
            │  - SharedMemory     │
            └──────────┬──────────┘
                       │
         ┌─────────────┴─────────────┐
         │                           │
┌────────▼──────────┐    ┌───────────▼───────────┐
│  AgentPool        │    │  TaskQueue             │
│  - Semaphore      │    │  - dependency graph    │
│  - runParallel()  │    │  - auto unblock        │
└────────┬──────────┘    │  - cascade failure     │
         │               └───────────────────────┘
┌────────▼──────────┐
│  Agent            │
│  - run()          │    ┌────────────────────────┐
│  - prompt()       │───►│  LLMAdapter            │
│  - stream()       │    │  - AnthropicAdapter    │
└────────┬──────────┘    │  - OpenAIAdapter       │
         │               │  - AzureOpenAIAdapter  │
         │               │  - BedrockAdapter      │
         │               │  - CopilotAdapter      │
         │               │  - GeminiAdapter       │
         │               │  - GrokAdapter         │
         │               │  - MiniMaxAdapter      │
         │               │  - DeepSeekAdapter     │
         │               │  - QiniuAdapter        │
         │               └────────────────────────┘
┌────────▼──────────┐
│  AgentRunner      │    ┌──────────────────────┐
│  - conversation   │───►│  ToolRegistry        │
│    loop           │    │  - defineTool()      │
│  - tool dispatch  │    │  - 6 built-in tools  │
└───────────────────┘    │  + delegate (opt-in) │
                         └──────────────────────┘

Core Concepts

Tools + MCP. Built-ins cover bash, file_read, file_write, file_edit, grep, and glob; custom tools use defineTool() + Zod; stdio MCP servers connect through connectMCPTools(). See tool configuration.
Observability. Wire onProgress for live lifecycle events, onTrace for structured spans, and renderTeamRunDashboard(result) for a static DAG dashboard. See observability.
Shared memory. Use the default in-process KV or bring Redis, Postgres, Engram, or any MemoryStore. See shared memory.
Context management. Use sliding windows, summarization, rule-based compaction, or a custom compressor for long-running agents. See context management.

Supported Providers

Change provider, model, and set the env var. The agent config shape stays the same.

const agent: AgentConfig = {
  name: 'my-agent',
  provider: 'anthropic',
  model: 'claude-sonnet-4-6',
  systemPrompt: 'You are a helpful assistant.',
}

Kind	How to configure	Services
Built-in shortcuts	Set `provider` to `anthropic`, `gemini`, `openai`, `azure-openai`, `copilot`, `grok`, `deepseek`, `minimax`, `qiniu`, or `bedrock`; the framework supplies the endpoint.	Anthropic, Gemini, OpenAI, Azure OpenAI, GitHub Copilot, xAI Grok, DeepSeek, MiniMax, Qiniu, AWS Bedrock
OpenAI-compatible endpoints	Set `provider: 'openai'` plus `baseURL` and, when needed, `apiKey`.	Ollama, vLLM, LM Studio, llama.cpp server, OpenRouter, Groq, Mistral

See docs/providers.md for env vars, model examples, local tool-calling, timeouts, and troubleshooting.

Production Checklist

Before going live, wire up the controls that protect token spend, recover from failure, and let you debug.

Concern	Knob	Where it lives
Bound the conversation	`maxTurns` per agent + `contextStrategy` (`sliding-window` / `summarize` / `compact` / `custom`)	`AgentConfig`
Cap tool output	`maxToolOutputChars` (or per-tool `maxOutputChars`) + `compressToolResults: true`	`AgentConfig` and `defineTool()`
Recover from failure	Per-task `maxRetries`, `retryDelayMs`, `retryBackoff` (exponential multiplier)	Task config used via `runTasks()`
Hard-cap spend	`maxTokenBudget` on the orchestrator	`OrchestratorConfig`
Catch stuck agents	`loopDetection` with `onLoopDetected: 'terminate'` (or a custom handler)	`AgentConfig`
Trace and audit	`onTrace` to your tracing backend; persist `renderTeamRunDashboard(result)`	`OrchestratorConfig`

Contributing

Issues, feature requests, and PRs are welcome. Some areas where contributions would be especially valuable:

Production examples. Real-world end-to-end workflows. See examples/production/README.md for the acceptance criteria and submission format.
Documentation. Guides, tutorials, and API docs.
Translations. Help translate this README into other languages. Open a PR.

Contributors

Contributor credits by area

Framework features

@ibrahimkzmv (token budget, context strategy, dependency-scoped context, tool presets, glob, MCP integration, configurable coordinator, CLI, dashboard rendering, trace event types)
@apollo-mg (context compaction fix, sampling parameters)
@tizerluo (onPlanReady, onAgentStream)
@CodingBangboo (planOnly mode)
@Xin-Mai (output schema validation)
@JasonOA888 (AbortSignal support)
@EchoOfZion (coordinator skip for simple goals)
@voidborne-d (OpenAI mixed content fix)
@NamelessNATM (agent delegation base implementation)
@MyPrototypeWhat (reasoning blocks, reasoning_effort, sampling parity, trace input/output)
@SiMinus (streaming reasoning events)

Provider integrations

@ibrahimkzmv (Gemini)
@hkalex (DeepSeek, MiniMax)
@marceloceccon (Grok)
@Klarline (Azure OpenAI)
@Deathwing (GitHub Copilot)
@JackChiang233 (Qiniu)
@CodingBangboo (AWS Bedrock)

Examples & cookbook

@mvanhorn (research aggregation, code review, meeting summarizer, Groq example, Mistral example)
@Kinoo0 (code review upgrade)
@Optimisttt (research aggregation upgrade)
@Agentscreator (Engram memory integration)
@fault-segment (contract-review DAG)
@HuXiangyu123 (cost-tiered example)
@zouhh22333-beep (translation/backtranslation)
@pei-pei45 (competitive monitoring)
@mmjwxbc (interview simulator)
@binghuaren96 (incident postmortem DAG)
@DaiMao-UT (paper replication triage)
@oooooowoooooo (rare disease information triage)
@CodingBangboo (Express customer support pipeline)

Docs & tests

@tmchow (llama.cpp docs)
@kenrogers (OpenRouter docs)
@jadegold55 (LLM adapter test coverage)

Star History

License

MIT

Open Multi-Agent

Real-world workflows (cookbook/)

Real-world workflows (`cookbook/`)