# modelmux

> Use this tool when you need to integrate multiple AI agents into a single workflow, enabling them to exchange data and leverage each other's strengths. Modelmux solves the problem of isolated AI models by allowing agents like Claude Code, Codex, and Perplexity to call each other directly, supporting various input formats such as text, code, images, and PDFs. It provides a flexible interface for passing files and receiving outputs, making it ideal for complex tasks that require collaboration between different AI models.

Canonical page: https://skillsregistry.net/skills/jrwoodcock-modelmux  
JSON: https://api.skillsregistry.net/v1/skills/jrwoodcock-modelmux

## Description

Enables AI agents like Claude Code, Codex, and Perplexity to call each other as tools directly from the terminal, supporting text, code, images, and PDFs passed by file path.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kbkud893lf)
- **Repository:** <https://github.com/JRWoodcock/modelmux>

## 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": "jrwoodcock-modelmux"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jrwoodcock-modelmux` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jrwoodcock-modelmux/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