add-ollama-provider

Route NanoClaw agent groups to a local Ollama model via configuration changes.

5|Updated Apr 2, 2026

Search Tags:#setup #container #ai-agent #anthropic #env-vars #ollama #local-model

Ready to run

npx skills add https://github.com/thmtz/nanoclaw-fleet --skill add-ollama-provider-thmtz

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: add-ollama-provider
Source: https://github.com/thmtz/nanoclaw-fleet/tree/main/.claude/skills/add-ollama-provider
Command: npx skills add https://github.com/thmtz/nanoclaw-fleet --skill add-ollama-provider-thmtz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.

Core Features & Use Cases

Route agent groups to a local Ollama instance for private, offline inference.
Minimize API costs by avoiding cloud calls and test with open-weight models locally.
Use case: Develop and benchmark multi-agent workflows entirely on the local host before deploying to cloud.

Quick Start

Configure your agent group to route to Ollama and start the fleet.

Frequently Asked Questions about add-ollama-provider

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

FAQPage Schema

How do I route a NanoClaw agent to a local Ollama model instead of the Anthropic API?▼

Route a NanoClaw agent to local Ollama by applying per-group configuration changes to container.json and shared Claude settings. Ollama natively speaks the Anthropic API, so no provider code changes are needed.

Do I need to modify provider code to use local Ollama models for my agents?▼

No code changes are needed to use local Ollama models because Ollama natively speaks the Anthropic v1/messages API. You only need to apply environment variable overrides and update the model setting.

What are the prerequisites for running agents against a local Ollama instance?▼

Running agents against local Ollama requires Ollama running on the host and a pulled Ollama model. You must then apply per-group configuration changes to container.json and shared Claude settings.

Why use a local Ollama model for multi-agent workflows instead of cloud APIs?▼

Use a local Ollama model to run agents privately offline, cut cloud API costs, and experiment with open-weight models. It allows you to develop and benchmark multi-agent workflows entirely on the local host.

What environment variables do I override to switch my agent group to Ollama?▼

Switching agent groups to Ollama requires applying environment variable overrides alongside a model setting update. These env var overrides replace the default Anthropic API configuration without altering provider code.