modelmux runs on your own machine — the client starts it, so there is no endpoint to ping. 49 installs a week from pypi.
Model multiplexer — route tasks to Codex, Gemini, and Claude CLIs with smart routing.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add modelmux -- uvx modelmux
{
"mcpServers": {
"modelmux": {
"command": "uvx",
"args": [
"modelmux"
]
}
}
}
[mcp_servers.modelmux]
command = "uvx"
args = ["modelmux"]
{
"mcpServers": {
"modelmux": {
"command": "uvx",
"args": [
"modelmux"
]
}
}
}
{
"servers": {
"modelmux": {
"type": "stdio",
"command": "uvx",
"args": [
"modelmux"
]
}
}
}
Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Delegate coding tasks from Claude Code, Codex or opencode to any model opencode can run.
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Answers built from our own checks of this server.