# Open Multi-Agent

> TypeScript-native multi-agent orchestration. A coordinator turns a goal into a task DAG, parallelizes the independent nodes, and synthesizes the result — three runtime dependencies, runs anywhere Node.js runs.

Open Multi-Agent (OMA) is an open-source (MIT) agent runtime, not a graph builder. You pass a goal, not a graph: a coordinator agent decomposes it into a task DAG, runs independent nodes in parallel, and returns a typed, schema-validated result. Each agent in a team can name its own model — Anthropic, OpenAI, a local Ollama, or a self-hosted endpoint — and they cooperate inside a single team. Tools are default-deny; Model Context Protocol (MCP) servers connect external systems under the same opt-in contract.

- Install: `npm create oma-app@latest`
- Package: `@open-multi-agent/core` (npm)
- License: MIT
- Runtime: Node.js 18+, three runtime dependencies

## Capabilities

- **Goal-driven coordinator**: you pass a goal, not a graph. A coordinator agent decomposes it into a task DAG, parallelizes independent nodes, and synthesizes the result.
- **Mix any model in one team**: each agent names its own model — Anthropic, Gemini, OpenAI, Bedrock, Azure, DeepSeek, or any OpenAI-compatible endpoint (13 built-in) — and they cooperate inside a single team.
- **Tools and MCP, default-deny**: an agent gets only the tools it lists. Model Context Protocol servers expose external systems under the same opt-in contract.
- **Streaming and structured output**: stream tokens and node-state transitions as the DAG fills, or await a typed, schema-validated object at the end of the run.
- **Cross-provider reasoning**: one thinking config maps to Anthropic thinking, Gemini thinkingConfig, and OpenAI reasoning_effort; reasoning streams as events, with opt-in preservation across a provider switch.
- **Built for production**: stay in the loop (onPlanReady / onApproval gates, runConsensus proposer→judge, loop detection), control spend (modelRouting, maxTokenBudget hard ceiling), and inspect any run (onTrace, a self-contained HTML dashboard, checkpoint/resume, best-effort secret redaction).

## Docs

- [Introduction](https://open-multi-agent.com/getting-started/introduction/): what open-multi-agent is, how goal-first orchestration differs from graph-first frameworks, and how the runtime is structured.
- [Quick Start](https://open-multi-agent.com/getting-started/quick-start/): scaffold a project with npm create oma-app, or install the core package and run your first auto-orchestrated team.
- [Three Ways to Run](https://open-multi-agent.com/getting-started/three-ways-to-run/): runAgent, runTeam, and runTasks — plus plan preview, plan replay, and consensus verification.
- [Orchestration Controls](https://open-multi-agent.com/guides/orchestration-controls/): team context injection, approval gates, cancellation, coordinator config, and fan-out.
- [Production Checklist](https://open-multi-agent.com/guides/production-checklist/): token budget, timeouts, retries, tool-output limits, loop detection, tracing, and tool grants.

## Reference

- [Providers](https://open-multi-agent.com/reference/providers/): configure hosted, cloud, and local model providers — built-in shortcuts, OpenAI-compatible endpoints, env vars, and local tool-calling.
- [MiniMax setup](https://open-multi-agent.com/reference/providers/minimax/): use MiniMax models in OMA via the built-in minimax provider.
- [Tool configuration](https://open-multi-agent.com/reference/tool-configuration/): grant built-in tools (default-deny), presets and allowlists, the filesystem sandbox, custom tools, and MCP.
- [Observability](https://open-multi-agent.com/reference/observability/): onProgress events, onTrace spans, and the static post-run dashboard.
- [Shared memory](https://open-multi-agent.com/reference/shared-memory/): a namespaced key-value store shared across a team, in-process or via a custom MemoryStore backend.
- [Checkpoint & resume](https://open-multi-agent.com/reference/checkpoint/): opt-in per-run snapshots over any MemoryStore — persist task progress and resume after a crash, abort, or restart with restore().
- [Context management](https://open-multi-agent.com/reference/context-management/): keep long runs under the token ceiling with context strategies, tool-result compression, and cross-provider reasoning.
- [Consensus](https://open-multi-agent.com/reference/consensus/): runConsensus proposer-to-judge verification, the per-task verify hook, and the shared token-budget invariant.
- [Model routing](https://open-multi-agent.com/reference/model-routing/): opt-in deterministic policy that routes orchestration phases to different models by phase, agent, task role, priority, or leaf.
- [CLI](https://open-multi-agent.com/reference/cli/): the JSON-first oma binary for shell and CI — commands, config files, output, and exit codes.

## Blog

- [Give Your TypeScript AI Agents Long-Term Memory with TencentDB-Agent-Memory](https://open-multi-agent.com/blog/agent-long-term-memory-tencentdb/): wiring OMA's MemoryStore to TencentDB-Agent-Memory for cross-run agent memory.
- [Goal-Driven Agent Orchestration vs Explicit Graphs: A TypeScript Framework Taxonomy](https://open-multi-agent.com/blog/goal-driven-vs-explicit-graphs/): a taxonomy of TypeScript multi-agent frameworks — goal-driven orchestration vs explicit graphs.
- [5 walls multi-agent frameworks hit](https://open-multi-agent.com/blog/multi-agent-framework-walls/): the engineering walls frameworks hit, with receipts from Mastra's .network() → Supervisor migration.
- [How to Run a Mixed-Model AI Agent Team in TypeScript?](https://open-multi-agent.com/blog/mixed-model-agent-team/): a walkthrough from a single-model baseline to a mixed-provider agent team.
- [Adding Multi-Agent Orchestration to a Vercel AI SDK App](https://open-multi-agent.com/blog/multi-agent-vercel-ai-sdk/): layering OMA orchestration onto an existing Vercel AI SDK app.

## Project

- [GitHub repository](https://github.com/open-multi-agent/open-multi-agent): source, examples, and issues.
- [Examples (cookbook)](https://open-multi-agent.com/examples/): runnable multi-agent recipes — contract review, competitive monitoring, incident postmortem, and more.
- [npm package](https://www.npmjs.com/package/@open-multi-agent/core)

## Optional

- [Full text for LLMs](https://open-multi-agent.com/llms-full.txt): capabilities, use cases, and FAQ assembled into one document.