Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Add Ollama Provider (NanoClaw)

Routes a NanoClaw agent group to a local Ollama model instead of the Anthropic API via env overrides and a model setting.

Dev & CodingAdvanced★ 30,471⑂ 12,865AI score 8/10Last updated: Aug 9, 2026

What it does

  • Points a chosen NanoClaw agent group at a local Ollama server (localhost:11434). Ollama speaks the Anthropic v1/messages API natively, so no provider code is required.
  • If ContainerConfig lacks env/blockedHosts, it walks you through the exact patches for src/container-config.ts and src/container-runner.ts (plus a Dockerfile permission fix).
  • Writes ANTHROPIC_BASE_URL, ANTHROPIC_API_KEY, and NO_PROXY into groups/<folder>/container.json, and sets "model" in the group's shared settings.json.
  • Optionally blocks api.anthropic.com by mapping it to 0.0.0.0 so accidental paid calls can't happen.
  • Includes build/restart commands, docker inspect verification, a clean revert path, and a troubleshooting section.

Who it's for

  • Anyone self-hosting NanoClaw who wants to cut API spend or run agents offline.
  • Developers comfortable with Docker and local LLM tooling.
  • People experimenting with open-weight models (gemma, qwen) as agent backends.

Examples

  1. "Switch my research agent group to local qwen3-coder" → pick group → patch config + settings → rebuild and restart.
  2. "Make sure nothing hits the Anthropic API" → adds blockedHosts and verifies ExtraHosts inside the running container.
  3. "Put it back on Claude" → removes the env/blockedHosts keys and model setting, restart only, no image rebuild.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/nanocoai/nanoclaw/HEAD/.claude/skills/add-ollama-provider/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .claude/skills/add-ollama-provider folder from the GitHub repo nanocoai/nanoclaw into my ~/.claude/skills/add-ollama-provider/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/nanocoai/nanoclaw.git && mkdir -p ~/.claude/skills && cp -r nanoclaw/.claude/skills/add-ollama-provider ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Install and start Ollama, then confirm it responds: curl -s http://localhost:11434/api/tags.
  2. Pull a model, e.g. ollama pull qwen3-coder.
  3. Clone the project: git clone https://github.com/nanocoai/nanoclaw.git
  4. Copy the skill into your skills folder: mkdir -p ~/.claude/skills && cp -r nanoclaw/.claude/skills/add-ollama-provider ~/.claude/skills/
  5. Open Claude Code from the NanoClaw project root and ask it to "route my agent group to Ollama".
  6. Answer the three prompts: which agent group, which model, and whether to block the Anthropic API.
  7. Verify afterwards with docker exec <container> env | grep ANTHROPIC and curl -s http://localhost:11434/api/ps.
View source on GitHub ↗License: MIT