ollama-launch

Name: ollama-launch
Availability: InStock
Author: Shichiyou

Configure environment variables and startup scripts to route CLI coding agents through a local Ollama server.

Updated Aug 23, 2026

Search Tags:#claude-code #launch #ollama #local-llm #model-routing #hermes-agent #cli-agent

Ready to run

npx skills add https://github.com/shichiyou/hermes-agent-001 --skill ollama-launch

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ollama-launch
Source: https://github.com/shichiyou/hermes-agent-001/tree/main/.devcontainer/hermes-backup/skills/autonomous-ai-agents/ollama-launch
Command: npx skills add https://github.com/shichiyou/hermes-agent-001 --skill ollama-launch

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Configuring CLI coding agents to run against local Ollama models can be tricky, requiring manual setup of environment variables and config files to avoid cloud endpoints.

Core Features & Use Cases

Route CLI agents such as Claude Code, Codex CLI, Copilot CLI, and Hermes through a local Ollama server for locally hosted inference.
Enable reproducible local testing and development by binding agents to local models and managing prompts.
Works with Ollama v0.20+ and requires that the Ollama server is running and models are pulled.

Quick Start

Log into your development environment and launch a target agent with a chosen Ollama model to start routing calls through the local Ollama server.

Frequently Asked Questions about ollama-launch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I route Claude Code or Codex CLI through a local Ollama server?▼

To route CLI coding agents through a local Ollama server, you use the ollama launch command. This configures environment variables and startup scripts to bind agent model calls to local models, avoiding cloud endpoints for local inference.

Can I use Copilot CLI or Hermes agents with local Ollama models?▼

Yes, you can route Copilot CLI and Hermes agents to local Ollama models. The skill binds these installed agent binaries to local models, managing prompts and enabling reproducible, container-friendly local development workflows.

What's the best way to set up environment variables for local LLM inference in CLI agents?▼

Setting up environment variables for local LLM inference is handled automatically by applying environment variable routing and model selection. This approach enforces reproducible configurations to ensure CLI agents consistently target local endpoints.

Do I need a specific Ollama version to bind local models to coding agents?▼

Yes, binding local models to coding agents requires Ollama v0.20 or higher. You must also have the Ollama server running, the target models already pulled, and your chosen agent binaries installed in your development environment.

Why does my CLI coding agent still connect to cloud endpoints instead of local Ollama?▼

If your CLI coding agent connects to cloud endpoints, you need to enforce environment variable routing. Launching the agent through local Ollama binds the model calls away from cloud endpoints, ensuring all inference stays local.