SwarmClaw provides a self hosted runtime and multi agent framework with memory, tools, schedules, and delegation.
Open source
24 alternativesopen-multi-agent
The open-multi-agent project provides a self-hosted TypeScript runtime with approvals and verifiable records.
About open-multi-agent
Open Multi-Agent is a self-hosted TypeScript runtime for running a single agent, an explicit task pipeline, or a goal-planned team. Consequential plan, dispatch, or tool actions can suspend for human approval, with requests stored beside checkpoints and bound to a SHA-256 hash of the reviewed content, and runs can resume after restart. A journal backend can record model inputs, tool calls and results, and context rewrites for offline byte-for-byte verification.
It works with user-supplied models and endpoints, including cloud providers, local servers such as Ollama, vLLM and llama-server, OpenAI-compatible endpoints, and AI SDK providers. It requires Node.js 20 or newer, with a maintained LTS release recommended for production, and live model runs need provider credentials while the starter demo uses scripted responses with no API key.
Key features
- Self-hosted TypeScript runtime for single agents, pipelines, and teams
- Durable approvals bound to SHA-256 hash of reviewer content
- Offline byte-for-byte verification of run journal
- Supports cloud, local, and OpenAI-compatible model providers
- Checkpoint store resumes suspended runs after restart
- Governance check on roles, order, dependencies, and review
Best for: Teams that need to self-host TypeScript agents with human approval and auditable run records.
Good for
- No telemetry or hosted control plane; users supply keys, models, and environment
- Starter demo runs locally with scripted responses and no model request
- Journal can be checked offline to confirm each block reproduces its source event
Watch out for
- Requires Node.js 20 or newer; Node.js 20 is an upstream-EOL compatibility window
- Live examples need provider credentials, such as OPENAI_API_KEY
- Verification reports an evicted context window as inconclusive and does not prove a file was never edited
open-multi-agent at a glance
- Category
- AI & Machine Learning › AI Agent Frameworks
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
open-multi-agent alternatives
Tools and sites you could use instead, ranked by how closely they match.
Hive supports applications that coordinate multiple AI agents through shared task workflows.
Open source
24 alternatives
Strands Agents SDK provides an open source toolkit for building and controlling production agents in Python and TypeScript.
Open source
24 alternatives
Nous combines AI chat, autonomous agents, developer agents, and chatbots in a TypeScript platform.
Open source
24 alternatives
VoltAgent provides a TypeScript framework and engineering platform for building AI agents.
Open source
24 alternatives
Aeon provides an AI agent framework that runs unattended on GitHub Actions and can drive Claude Code, Grok, and Codex.
Open source
24 alternativesPopular in AI Agent Frameworks
Well-known listings from the same topic.
Uplizd Unicornunicorn.uplizd.aiWebagentforge.netAbility AIability.aiHaystackhaystack.deepset.aiLangChainlangchain.comPromptShuttlepromptshuttle.com
open-multi-agent FAQ
What is needed to run OMA?
Node.js 20 or newer, with a currently maintained LTS release recommended for production.
Do I need an API key to try the demo?
No. The starter local demo uses scripted model responses and makes no model request.
What models can OMA use?
Hosted providers, local servers such as Ollama, vLLM and llama-server, OpenAI-compatible endpoints, and AI SDK providers, using your own keys and endpoints.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.