Octopal — AI skill for Claude Code
Multi-model AI agent orchestrator.
How to install Octopal
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open gilhyun/Octopal and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Octopal does
Multi-model AI agent orchestrator. Run Claude, GPT, and Ollama agents in one workspace with group chat, smart routing, and per-agent model assignment.
Alternatives in AI
- Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
- Open Dots — Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Man 5.5k ★
- Chat Ollama — ChatOllama is an open source agentic app for running AI agents across local and hosted models 3.5k ★
README
Octopal
Multi-Model AI Agent Orchestration
Run Claude, GPT, and Ollama agents together in one workspace.
Assign the right model to each role. Let them collaborate.
Free & open source — macOS & Windows.
🌐 octopal.app | English | 한국어
What is Octopal?
Octopal is a **multi-model AI agent orchestrato
Related Skills
Klaatcode
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the r
Plenipo
Free, local-first Windows desktop app for AI workforce and multi-agent orchestration. Coordinate Claude Code,
Octoroute
Smart HTTP router for local LLMs (Ollama, LM Studio, llama.cpp). Rule-based + LLM-powered routing, health chec
LLM Fusion
OpenAI and Anthropic compatible LLM proxy for Ollama Cloud — panel→judge→synth fusion + smart routing, with ta
Loushang
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool
Zenith
Self-hosted, local-first AI workspace on your own Ollama models — chat, a Claude-Code-class coding agent, deep
Related Agents
GPT Chat
Conducts a conversation with a GPT model (Codex) as a separate conversational partner—the thread persists betw
Ocx GPT 5 4 Mini
Delegate work to gpt-5.4-mini (native) via opencodex routing. General-purpose worker/explorer on that model. N
Local Worker
Coding worker on a local model (Ollama, LM Studio, vLLM) served by the multi-model gateway's upstream. Use whe