{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ollama-local",
    "name": "Ollama Local",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/Timverhoogt/ollama-local",
    "canonicalUrl": "https://clawhub.ai/Timverhoogt/ollama-local",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ollama-local",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ollama-local",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/models.md",
      "scripts/ollama.py",
      "scripts/ollama_tools.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ollama-local"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/ollama-local",
    "agentPageUrl": "https://openagent3.xyz/skills/ollama-local/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ollama-local/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ollama-local/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Ollama Local",
        "body": "Work with local Ollama models for inference, embeddings, and tool use."
      },
      {
        "title": "Configuration",
        "body": "Set your Ollama host (defaults to http://localhost:11434):\n\nexport OLLAMA_HOST=\"http://localhost:11434\"\n# Or for remote server:\nexport OLLAMA_HOST=\"http://192.168.1.100:11434\""
      },
      {
        "title": "Quick Reference",
        "body": "# List models\npython3 scripts/ollama.py list\n\n# Pull a model\npython3 scripts/ollama.py pull llama3.1:8b\n\n# Remove a model\npython3 scripts/ollama.py rm modelname\n\n# Show model details\npython3 scripts/ollama.py show qwen3:4b\n\n# Chat with a model\npython3 scripts/ollama.py chat qwen3:4b \"What is the capital of France?\"\n\n# Chat with system prompt\npython3 scripts/ollama.py chat llama3.1:8b \"Review this code\" -s \"You are a code reviewer\"\n\n# Generate completion (non-chat)\npython3 scripts/ollama.py generate qwen3:4b \"Once upon a time\"\n\n# Get embeddings\npython3 scripts/ollama.py embed bge-m3 \"Text to embed\""
      },
      {
        "title": "Model Selection",
        "body": "See references/models.md for full model list and selection guide.\n\nQuick picks:\n\nFast answers: qwen3:4b\nCoding: qwen2.5-coder:7b\nGeneral: llama3.1:8b\nReasoning: deepseek-r1:8b"
      },
      {
        "title": "Tool Use",
        "body": "Some local models support function calling. Use ollama_tools.py:\n\n# Single request with tools\npython3 scripts/ollama_tools.py single qwen2.5-coder:7b \"What's the weather in Amsterdam?\"\n\n# Full tool loop (model calls tools, gets results, responds)\npython3 scripts/ollama_tools.py loop qwen3:4b \"Search for Python tutorials and summarize\"\n\n# Show available example tools\npython3 scripts/ollama_tools.py tools\n\nTool-capable models: qwen2.5-coder, qwen3, llama3.1, mistral"
      },
      {
        "title": "OpenClaw Sub-Agents",
        "body": "Spawn local model sub-agents with sessions_spawn:\n\n# Example: spawn a coding agent\nsessions_spawn(\n    task=\"Review this Python code for bugs\",\n    model=\"ollama/qwen2.5-coder:7b\",\n    label=\"code-review\"\n)\n\nModel path format: ollama/<model-name>"
      },
      {
        "title": "Parallel Agents (Think Tank Pattern)",
        "body": "Spawn multiple local agents for collaborative tasks:\n\nagents = [\n    {\"label\": \"architect\", \"model\": \"ollama/gemma3:12b\", \"task\": \"Design the system architecture\"},\n    {\"label\": \"coder\", \"model\": \"ollama/qwen2.5-coder:7b\", \"task\": \"Implement the core logic\"},\n    {\"label\": \"reviewer\", \"model\": \"ollama/llama3.1:8b\", \"task\": \"Review for bugs and improvements\"},\n]\n\nfor a in agents:\n    sessions_spawn(task=a[\"task\"], model=a[\"model\"], label=a[\"label\"])"
      },
      {
        "title": "Direct API",
        "body": "For custom integrations, use the Ollama API directly:\n\n# Chat\ncurl $OLLAMA_HOST/api/chat -d '{\n  \"model\": \"qwen3:4b\",\n  \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}],\n  \"stream\": false\n}'\n\n# Generate\ncurl $OLLAMA_HOST/api/generate -d '{\n  \"model\": \"qwen3:4b\",\n  \"prompt\": \"Why is the sky blue?\",\n  \"stream\": false\n}'\n\n# List models\ncurl $OLLAMA_HOST/api/tags\n\n# Pull model\ncurl $OLLAMA_HOST/api/pull -d '{\"name\": \"phi3:mini\"}'"
      },
      {
        "title": "Troubleshooting",
        "body": "Connection refused?\n\nCheck Ollama is running: ollama serve\nVerify OLLAMA_HOST is correct\nFor remote servers, ensure firewall allows port 11434\n\nModel not loading?\n\nCheck VRAM: larger models may need CPU offload\nTry a smaller model first\n\nSlow responses?\n\nModel may be running on CPU\nUse smaller quantization (e.g., :7b instead of :30b)\n\nOpenClaw sub-agent falls back to default model?\n\nEnsure ollama:default auth profile exists in OpenClaw config\nCheck model path format: ollama/modelname:tag"
      }
    ],
    "body": "Ollama Local\n\nWork with local Ollama models for inference, embeddings, and tool use.\n\nConfiguration\n\nSet your Ollama host (defaults to http://localhost:11434):\n\nexport OLLAMA_HOST=\"http://localhost:11434\"\n# Or for remote server:\nexport OLLAMA_HOST=\"http://192.168.1.100:11434\"\n\nQuick Reference\n# List models\npython3 scripts/ollama.py list\n\n# Pull a model\npython3 scripts/ollama.py pull llama3.1:8b\n\n# Remove a model\npython3 scripts/ollama.py rm modelname\n\n# Show model details\npython3 scripts/ollama.py show qwen3:4b\n\n# Chat with a model\npython3 scripts/ollama.py chat qwen3:4b \"What is the capital of France?\"\n\n# Chat with system prompt\npython3 scripts/ollama.py chat llama3.1:8b \"Review this code\" -s \"You are a code reviewer\"\n\n# Generate completion (non-chat)\npython3 scripts/ollama.py generate qwen3:4b \"Once upon a time\"\n\n# Get embeddings\npython3 scripts/ollama.py embed bge-m3 \"Text to embed\"\n\nModel Selection\n\nSee references/models.md for full model list and selection guide.\n\nQuick picks:\n\nFast answers: qwen3:4b\nCoding: qwen2.5-coder:7b\nGeneral: llama3.1:8b\nReasoning: deepseek-r1:8b\nTool Use\n\nSome local models support function calling. Use ollama_tools.py:\n\n# Single request with tools\npython3 scripts/ollama_tools.py single qwen2.5-coder:7b \"What's the weather in Amsterdam?\"\n\n# Full tool loop (model calls tools, gets results, responds)\npython3 scripts/ollama_tools.py loop qwen3:4b \"Search for Python tutorials and summarize\"\n\n# Show available example tools\npython3 scripts/ollama_tools.py tools\n\n\nTool-capable models: qwen2.5-coder, qwen3, llama3.1, mistral\n\nOpenClaw Sub-Agents\n\nSpawn local model sub-agents with sessions_spawn:\n\n# Example: spawn a coding agent\nsessions_spawn(\n    task=\"Review this Python code for bugs\",\n    model=\"ollama/qwen2.5-coder:7b\",\n    label=\"code-review\"\n)\n\n\nModel path format: ollama/<model-name>\n\nParallel Agents (Think Tank Pattern)\n\nSpawn multiple local agents for collaborative tasks:\n\nagents = [\n    {\"label\": \"architect\", \"model\": \"ollama/gemma3:12b\", \"task\": \"Design the system architecture\"},\n    {\"label\": \"coder\", \"model\": \"ollama/qwen2.5-coder:7b\", \"task\": \"Implement the core logic\"},\n    {\"label\": \"reviewer\", \"model\": \"ollama/llama3.1:8b\", \"task\": \"Review for bugs and improvements\"},\n]\n\nfor a in agents:\n    sessions_spawn(task=a[\"task\"], model=a[\"model\"], label=a[\"label\"])\n\nDirect API\n\nFor custom integrations, use the Ollama API directly:\n\n# Chat\ncurl $OLLAMA_HOST/api/chat -d '{\n  \"model\": \"qwen3:4b\",\n  \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}],\n  \"stream\": false\n}'\n\n# Generate\ncurl $OLLAMA_HOST/api/generate -d '{\n  \"model\": \"qwen3:4b\",\n  \"prompt\": \"Why is the sky blue?\",\n  \"stream\": false\n}'\n\n# List models\ncurl $OLLAMA_HOST/api/tags\n\n# Pull model\ncurl $OLLAMA_HOST/api/pull -d '{\"name\": \"phi3:mini\"}'\n\nTroubleshooting\n\nConnection refused?\n\nCheck Ollama is running: ollama serve\nVerify OLLAMA_HOST is correct\nFor remote servers, ensure firewall allows port 11434\n\nModel not loading?\n\nCheck VRAM: larger models may need CPU offload\nTry a smaller model first\n\nSlow responses?\n\nModel may be running on CPU\nUse smaller quantization (e.g., :7b instead of :30b)\n\nOpenClaw sub-agent falls back to default model?\n\nEnsure ollama:default auth profile exists in OpenClaw config\nCheck model path format: ollama/modelname:tag"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Timverhoogt/ollama-local",
    "publisherUrl": "https://clawhub.ai/Timverhoogt/ollama-local",
    "owner": "Timverhoogt",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ollama-local",
    "downloadUrl": "https://openagent3.xyz/downloads/ollama-local",
    "agentUrl": "https://openagent3.xyz/skills/ollama-local/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ollama-local/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ollama-local/agent.md"
  }
}