skills.rest
CjLogic
CjLogicCOMMUNITY
Explore all skills by this author →
Website𝕏@OnPointToolsGitHub

add-ollama-provider

Route a NanoCrew agent group to a local Ollama model via environment overrides.

Updated Aug 23, 2026
Search Tags:#container#cost-saving#ollama#provider#local-model#nanocrew#open-weight
One-click install
npx skills add https://github.com/CjLogic/nanocrew --skill add-ollama-provider
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-ollama-provider
Source: https://github.com/CjLogic/nanocrew/tree/main/.codex/skills/add-ollama-provider
Command: npx skills add https://github.com/CjLogic/nanocrew --skill add-ollama-provider

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Routes a NanoCrew agent group to a local Ollama model instead of the Anthropic API, enabling offline experimentation and reduced external API costs.

Core Features & Use Cases

  • Local execution against a locally hosted Ollama model with no external API calls.
  • No provider code changes needed; uses existing Anthropic-compatible endpoints via env overrides and a model setting.
  • Use cases include development, testing, and cost-conscious deployments on a developer workstation or secure environment.

Quick Start

Point your agent group to a running Ollama instance and apply the env overrides and model setting as described.

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 NanoCrew agent group to a local Ollama model?▼

Routing a NanoCrew agent to Ollama involves applying environment variable overrides and setting a local model. This switches execution from the Anthropic API to your local instance.

Can I run NanoCrew agents offline using a local Ollama model?▼

Yes, you can run NanoCrew agents offline by routing them to a local Ollama model. This enables local execution against locally hosted open-weight models with no external API calls required.

Do I need to change provider code to use Ollama with NanoCrew?▼

No provider code changes are needed to use Ollama with NanoCrew. The setup uses existing Anthropic-compatible endpoints via environment overrides and a model setting for local execution.

What is the best way to reduce external API costs when testing NanoCrew agents?▼

The best way to reduce external API costs for NanoCrew is routing agent groups to a local Ollama model. This enables cost-conscious deployments and offline experimentation on a developer workstation.

Does the Ollama provider override support existing Anthropic-compatible endpoints?▼

Yes, the Ollama provider override supports existing Anthropic-compatible endpoints. It leverages environment variables to redirect NanoCrew agent traffic to your local Ollama instance seamlessly.

Related Skills

Explore More Software Engineering Skills→
jeffreykthomasjeffreykthomas

add-ollama-tool

Expose on-host Ollama models to NanoClaw agents via an MCP server.

Community
Intermediate
breakingcircuits1337breakingcircuits1337

ollama

Execute large language models locally without internet API calls.

Community
Intermediate
QredenceQredence
108

dspy-agent-framework-integration

Integrate DSPy with the Microsoft Agent Framework for typed signatures and orchestration.

Official
Advanced
NovaAI-innovationNovaAI-innovation

model-discovery

Fetch current model names from AI providers and classify them into performance tiers.

Community
Intermediate