Flagged: reads sensitive env vars. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by JackChen-me · MCP Server · ★ 6.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is open-multi-agent safe to install? View the security audit →
Open Multi-Agent TypeScript framework for multi-agent orchestration. One call from goal to result — the framework decomposes it into tasks, resolves dependencies, and runs agents in parallel. 3 runtime dependencies · 27 source files · Deploys anywhere Node.js runs · Mentioned in Latent Space AI News English | 中文 Why Open Multi-Agent? Goal In, Result Out — . A coordinator agent auto-decomposes the goal into a task DAG with dependencies and assignees, runs independent tasks in parallel, and synthesizes the final output. No manual task definitions or graph wiring required. TypeScript-Native — Built for the Node.js ecosystem. , import, run. No Python runtime, no subprocess bridge, no sidecar services. Embed in Express, Next.js, serverless functions, or CI/CD pipelines. Auditable and Lightweight — 3 runtime dependencies (, , ). 27 source files. The entire codebase is readable in an afternoon. Model Agnostic — Claude, GPT, Gemma 4, and local models (O
| Stars | 6,080 |
| Forks | 2,347 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.9634413839263/100 |
| Open Issues | 11 |
| Last Updated | 2026-05-08 |
| Created | 2026-03-31 |
| Platforms | claude-code, gemini, mcp, node |
| Est. Tokens | ~190k |
These tools work well together with open-multi-agent for enhanced workflows:
Looking for a open-multi-agent alternative? If you're comparing open-multi-agent with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w
The pretty much "official" DSPy framework for Typescript
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in pl
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - c
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/G
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,
Explore other popular mcp server tools:
open-multi-agent is From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration with MCP and live tracing. Three runtime dependencies.. It is categorized as a MCP Server with 6.1k GitHub stars.
open-multi-agent is primarily written in TypeScript. It covers topics such as agent-framework, ai-agents, anthropic.
You can find installation instructions and usage details in the open-multi-agent GitHub repository at github.com/JackChen-me/open-multi-agent. The project has 6.1k stars and 2347 forks, indicating an active community.
open-multi-agent is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to open-multi-agent on Agent Skills Hub include repomix, ax, ruby_llm. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: