Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Add Ollama Provider (NanoClaw)

Reroutes a NanoClaw agent group to a local Ollama model instead of the Anthropic API — no provider code required.

Dev & CodingAdvanced★ 30,471⑂ 12,865AI score 7/10Last updated: Aug 9, 2026

What it does

Points a NanoClaw agent group at a locally running Ollama server instead of the Anthropic API. Because Ollama exposes an Anthropic-compatible v1/messages endpoint, no new provider code is needed — only environment overrides (ANTHROPIC_BASE_URL, ANTHROPIC_API_KEY, NO_PROXY) plus a model setting.

The runbook covers: checking/adding env and blockedHosts to ContainerConfig and container-runner.ts, fixing home-dir permissions in the Dockerfile, editing groups/<folder>/container.json, writing model into the group's shared settings.json, rebuilding and restarting via launchd/systemd, and verifying with docker inspect and Ollama's /api/ps. It also documents blocking api.anthropic.com (mapped to 0.0.0.0) to prevent accidental spend, a revert procedure, and four common failure modes.

Who it's for

  • NanoClaw operators who want to cut API costs or go fully local
  • Teams needing open-weight models in offline or restricted networks
  • Developers comfortable with Docker, pnpm builds and service managers

Caveat: this is repo-specific. It assumes NanoClaw's file layout, SQLite DB and build scripts.

Examples

  1. "Switch my research agent group to qwen3-coder" — edits container.json + settings.json, rebuilds, restarts.
  2. "Make sure I never accidentally hit the paid API" — adds blockedHosts: ["api.anthropic.com"] so the container can't reach it.
  3. "Agent replies but Ollama shows no activity" — walks the troubleshooting path (missing lowercase no_proxy).

· · · Install guide · · ·

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 /tmp/nanoclaw && mkdir -p ~/.claude/skills && cp -r /tmp/nanoclaw/.claude/skills/add-ollama-provider ~/.claude/skills/

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

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/nanocoai/nanoclaw.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r nanoclaw/.claude/skills/add-ollama-provider ~/.claude/skills/
  5. Prerequisites: install and start Ollama, verify with curl -s http://localhost:11434/api/tags, then pull a model with ollama pull <model>.
  6. Launch Claude Code from your NanoClaw project root and ask: "Use add-ollama-provider to move group <name> to Ollama".
  7. Follow the build (pnpm run build) and service restart steps, then verify with docker exec <container> env | grep ANTHROPIC.
View source on GitHub ↗License: MIT