Clutch — AI skill for Claude Code
Provider-neutral LLM router and model orchestration engine with auto-learning and budget zones.
How to install Clutch
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ellmos-ai/clutch and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Clutch does
Provider-neutral LLM router and model orchestration engine with auto-learning and budget zones.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
- Setup Watch Skill — One-shot setup for Watch Skill — installs the engine, bootstraps ffmpeg/yt-dlp, registers the MCP server in ev 315 ★
README
[English](README.md) · [Deutsch](README_de.md) · [Español](README_es.md) · [简体中文](README_zh-Hans.md) · [日本語](README_ja.md) · [Русский](README_ru.md)
clutch
Provider-neutral LLM orchestration engine and model router with auto-learning
[](https://github.com/ellmos-ai/clutch/releases) [](https://github.com/ellmos-ai/clutch/actions) [](https://github.com/ellmos-ai/clutch) [](https://www.python.org/) [](https://github.com/ellmos-ai/clutch) [](LICENSE) [](https://github.com/ellmos-ai/clutch) [](SECURITY.md) [](https://github.com/astral-sh/ruff) [](SECURITY.md) [](SECURITY.md) [](SECURITY.md) [](https://github.com/ellmos-ai) [](https://github.com/open-bricks) [![Discovery: l
Related Skills
Gremlord
Run Claude Code on any model, with a budget — multi-provider router, LLM-triaged tier routing, spend tracking
Auto Model Router
Cache-, quota- and capability-aware LLM router with a Claude Code shim
Infinite Claude Code
Infinite, 100% Free, Zero-latency Multi-provider AI Router for Claude Code CLI & Desktop with real-time SSE st
Modelweaver
Multi-provider model orchestration proxy for Claude Code. Route agent roles (planning, coding, research) to di
Fuigo
A general-purpose, multi-provider AI agent engine. Tools, orchestration, persistent memory, and application in
Agent World
A local, vendor-agnostic voxel-world control room for coding-agent CLIs (Claude Code, Codex, Gemini, opencode,
Related Agents
Provider Tester
Use this agent when you need to test, debug, or validate LLM provider configurations. This includes verifying
Budget
AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits
Router Haiku
Worker subagent dispatched by the auto-model-router for trivial tasks — reads, lists, lookups, quick edits, cl