# multi-agent-broker

> multi-agent-broker — marsyanggo-multi-agent-broker. Use this tool when you need to integrate multiple large language models (LLMs) from different vendors into a unified team, enabling seamless collaboration and capability-based task routing across various platforms. It solves the problem of vendor lock-in by allowing tasks to be dispatched and picked up by the most suitable LLM, regardless of the host or vendor. This tool is ideal for use cases where a single vendor's stack is insufficient, and tasks require the expertise of LLMs from multiple vendors.

Canonical page: https://skillsregistry.net/skills/marsyanggo-multi-agent-broker  
JSON: https://api.skillsregistry.net/v1/skills/marsyanggo-multi-agent-broker

## Description

Make LLMs from different vendors collaborate as one team. Capability-based task routing across Claude / GPT / Gemini / Ollama. Lead dispatches → broker filter-broadcasts → workers (any LLM, any host) pick up matching tasks. Single-vendor stacks already have subagents — this is for when the right tool for the job lives in another vendor's stack.

## Trust

- **Trust score (0–1):** 0.55
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/marsyanggo/multi-agent-broker)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "marsyanggo-multi-agent-broker"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/marsyanggo-multi-agent-broker` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/marsyanggo-multi-agent-broker/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt