agentleFS
ss2codess2code/nanoclaw-ops/.claude/skills/add-ollama-provider/SKILL.md

add-ollama-provider

Skill1 starsChanged 43 days agoMITView on GitHub

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.

  • Reads credentials

7 other projects use a version of this, 6 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • qwibitaiSkill

    add-iron-proxy

    Install or refresh Iron Proxy and its official Iron Control web console for NanoClaw. Use when selecting the Iron gateway, adding its management UI, configuring credentials and grants, or restoring the proxy, approval bridge, and agent guidance.

    Also in 4 projects that use this

  • qwibitaiSkill

    add-mattermost

    Add a self-hosted or cloud Mattermost bot channel through the Chat SDK bridge, reusing a healthy server when available and linking to official server setup guidance when needed.

    Also in 4 projects that use this

  • nanocoaiSkill

    add-cursor

    Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Cursor-account sign-in or API key, held by the credential gateway. Per-group via `ncl groups config update --provider cursor`. Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider).

    Also in 3 projects that use this

  • +5 more from TomGranot
  • +1 more from qwibitai

The file

We split this skill into the rules it gives an agent

12 rules. 5 are common, 0 are distinctive, and 7 are very specific to this project.

  • 5

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    If either count is 0, apply the changes in steps 1a and 1b.

    line 26
  2. Very specific:

    If it shows chmod 755, change it to chmod 777 so any uid can write there.

    line 72
  3. Common:

    Ask the user (plain text, not AskUserQuestion):

    line 77
  4. Very specific:

    Read groups/<FOLDER>/container.json.

    line 87
  5. Common:

    Read the agent group's shared Claude settings:

    line 110
  6. Very specific:

    Add "model": "<MODEL>" to that settings file.

    line 118
  7. Very specific:

    If the file already has content, merge the model key in — don't overwrite existing keys.

    line 126
  8. Common:

    Run from your NanoClaw project root:

    line 133
  9. Very specific:

    Remove the env and blockedHosts keys from groups/<FOLDER>/container.json

    line 164
  10. Very specific:

    Remove "model" from the shared settings file

    line 165
  11. Common:

    No rebuild needed — both files are read at container spawn time.

    line 168
  12. Very specific:

    Add a line to groups/<FOLDER>/CLAUDE.md telling it what model it runs on.

    line 179

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Add Ollama Provider

Routes an agent group to a local Ollama instance instead of the Anthropic API. See docs/ollama.md for how this works and the tradeoffs involved.

Prerequisites

  1. Ollama is installed and running on the host — verify: curl -s http://localhost:11434/api/tags
  2. A model is pulled — e.g. ollama pull gemma4 or ollama pull qwen3-coder
  3. The agent group already exists — run /init-first-agent first if needed

1. Check source support

The feature requires two fields in ContainerConfig (env and blockedHosts) and their corresponding wiring in container-runner.ts. Check if already present:

grep -c 'blockedHosts' src/container-config.ts src/container-runner.ts

If either count is 0, apply the changes in steps 1a and 1b. Otherwise skip to step 2.

1a. Extend ContainerConfig

In src/container-config.ts, add to the ContainerConfig interface:

env?: Record<string, string>;
blockedHosts?: string[];

And in readContainerConfig, add inside the returned object:

env: raw.env,
blockedHosts: raw.blockedHosts,

1b. Wire into container-runner

In src/container-runner.ts, after the NANOCLAW_MCP_SERVERS block, add:

// Per-agent-group env overrides — applied last to win over OneCLI values.
if (containerConfig.env) {
  for (const [key, value] of Object.entries(containerConfig.env)) {
    args.push('-e', `${key}=${value}`);
  }
}

// Blocked hosts: resolve to 0.0.0.0 so they are unreachable inside the container.
if (containerConfig.blockedHosts) {
  for (const host of containerConfig.blockedHosts) {
    args.push('--add-host', `${host}:0.0.0.0`);
  }
}

1c. Fix home directory permissions (if not already done)

The container may run as your host uid (not uid 1000). Check the Dockerfile:

grep 'chmod.*home/node' container/Dockerfile

If it shows chmod 755, change it to chmod 777 so any uid can write there. Then rebuild the container image: ./container/build.sh

2. Identify the setup

Ask the user (plain text, not AskUserQuestion):

  1. Which agent group? List available groups: pnpm exec tsx scripts/q.ts data/v2.db "SELECT folder, name FROM agent_groups;"
  2. Which Ollama model? List available: curl -s http://localhost:11434/api/tags | grep '"name"'
  3. Block Anthropic API? Recommended yes — prevents accidental spend if config drifts.

Record as FOLDER, MODEL, and BLOCK_ANTHROPIC.

3. Configure container.json

Read groups/<FOLDER>/container.json. Add (or merge into) an env block and optionally blockedHosts:

{
  "env": {
    "ANTHROPIC_BASE_URL": "http://host.docker.internal:11434",
    "ANTHROPIC_API_KEY": "ollama",
    "NO_PROXY": "host.docker.internal",
    "no_proxy": "host.docker.internal"
  },
  "blockedHosts": ["api.anthropic.com"]
}

Omit blockedHosts if the user declined step 2.

Why these vars: ANTHROPIC_BASE_URL redirects the Anthropic SDK to Ollama. ANTHROPIC_API_KEY=ollama satisfies the SDK's key requirement (Ollama ignores it). NO_PROXY bypasses the OneCLI HTTPS proxy for requests to host.docker.internal so they reach Ollama directly instead of going through the credential gateway.

4. Set the model

Read the agent group's shared Claude settings:

# Find the agent group ID
AG_ID=$(pnpm exec tsx scripts/q.ts data/v2.db "SELECT id FROM agent_groups WHERE folder='<FOLDER>';")
SETTINGS=data/v2-sessions/$AG_ID/.claude-shared/settings.json

Add "model": "<MODEL>" to that settings file. Create the file if it doesn't exist:

{
  "model": "gemma4:latest"
}

If the file already has content, merge the model key in — don't overwrite existing keys.

Why here and not container.json: Claude Code reads its model from its own settings file, not from env vars. This file is bind-mounted into the container as ~/.claude/settings.json.

5. Build and restart

Run from your NanoClaw project root:

export PATH="/opt/homebrew/bin:$PATH"
pnpm run build
source setup/lib/install-slug.sh
launchctl unload ~/Library/LaunchAgents/$(launchd_label).plist
launchctl load   ~/Library/LaunchAgents/$(launchd_label).plist
# Linux: systemctl --user restart $(systemd_unit)

6. Verify

Send a message to the agent. Then confirm:

# Ollama shows the model as active
curl -s http://localhost:11434/api/ps | grep '"name"'

# Container has the right env vars
CTR=$(docker ps --filter "name=nanoclaw-v2-<FOLDER>" --format "{{.Names}}" | head -1)
docker inspect "$CTR" --format '{{json .HostConfig.ExtraHosts}}'
docker exec "$CTR" env | grep ANTHROPIC

Expected: api.anthropic.com:0.0.0.0 in ExtraHosts, ANTHROPIC_BASE_URL=http://host.docker.internal:11434.

Reverting to Claude

To switch back to the Anthropic API:

  1. Remove the env and blockedHosts keys from groups/<FOLDER>/container.json
  2. Remove "model" from the shared settings file
  3. Restart the service

No rebuild needed — both files are read at container spawn time.

Troubleshooting

Agent hangs, no response: Ollama may be loading the model cold (large models take 10–30s). Watch curl -s http://localhost:11434/api/ps — the model appears once loaded.

"model not found" error in container logs: The model name in settings.json doesn't match what Ollama has. Run ollama list on the host and use the exact name shown.

Responses claim to be Claude: The model was trained on data that includes Claude conversations. Add a line to groups/<FOLDER>/CLAUDE.md telling it what model it runs on.

Agent responds but Ollama shows no activity: NO_PROXY may not have taken effect for http_proxy (lowercase). Add both NO_PROXY and no_proxy to the env block.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.