[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-docker-docker-model-runner":3,"mdc-33lz65-key":31,"related-org-docker-docker-model-runner":734,"related-repo-docker-docker-model-runner":783},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":20,"repoUrl":21,"updatedAt":22,"license":23,"forks":24,"topics":25,"repo":26,"sourceUrl":29,"mdContent":30},"docker-model-runner","run local LLM inference with Docker","Skills for using Docker Model Runner to run local LLM inference",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"docker","Docker","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdocker.png",[12,16,19],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"Machine Learning","machine-learning",{"name":9,"slug":8,"type":15},605,"https:\u002F\u002Fgithub.com\u002Fdocker\u002Fmodel-runner","2026-07-12T08:15:13.251096",null,137,[],{"repoUrl":21,"stars":20,"forks":24,"topics":27,"description":28},[],"Docker Model Runner","https:\u002F\u002Fgithub.com\u002Fdocker\u002Fmodel-runner\u002Ftree\u002FHEAD\u002Fcmd\u002Fcli\u002Fcommands\u002Fskills\u002Fdocker-model-runner","---\nname: docker-model-runner\ndescription: Skills for using Docker Model Runner to run local LLM inference\n---\n\n# Docker Model Runner\n\nDocker Model Runner (DMR) makes it easy to run AI models locally using Docker. This skill helps you effectively use Docker Model Runner for local LLM inference in your development workflow.\n\n## Workflow\n\nWhen helping users with local LLM inference using Docker Model Runner:\n\n1. **Check if Docker Model Runner is available** by running `docker model version`\n\n2. **List available models** with `docker model list` to see what's already pulled\n\n3. **Search for models** on Docker Hub or HuggingFace:\n   - `docker model search \u003Cquery>` to find models\n   - Popular models include: `ai\u002Fgemma3`, `ai\u002Fllama3.2`, `ai\u002Fsmollm2`, `ai\u002Fqwen3`\n\n4. **Pull models** before running: `docker model pull \u003Cmodel>`\n\n5. **Run models** for inference:\n   - One-time prompt: `docker model run ai\u002Fsmollm2 \"Your prompt here\"`\n   - Interactive chat: `docker model run ai\u002Fsmollm2`\n   - Pre-load model: `docker model run --detach ai\u002Fsmollm2`\n\n6. **Use the OpenAI-compatible API** for programmatic access:\n   - Endpoint: `http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\u002Fchat\u002Fcompletions`\n   - This is compatible with OpenAI client libraries\n\n## API Usage\n\nDocker Model Runner exposes an OpenAI-compatible REST API:\n\n```bash\n# Chat completions\ncurl http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"ai\u002Fsmollm2\",\n    \"messages\": [\n      {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n      {\"role\": \"user\", \"content\": \"Hello!\"}\n    ]\n  }'\n```\n\nFor Python with the OpenAI library:\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI(\n    base_url=\"http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\",\n    api_key=\"not-needed\"  # API key not required for local inference\n)\n\nresponse = client.chat.completions.create(\n    model=\"ai\u002Fsmollm2\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}]\n)\n```\n\n## Key Commands\n\n| Command | Description |\n|---------|-------------|\n| `docker model run \u003Cmodel> [prompt]` | Run a model with optional prompt |\n| `docker model pull \u003Cmodel>` | Pull a model from registry |\n| `docker model list` | List downloaded models |\n| `docker model search \u003Cquery>` | Search for models |\n| `docker model ps` | Show running models |\n| `docker model rm \u003Cmodel>` | Remove a model |\n| `docker model inspect \u003Cmodel>` | Show model details |\n\n## Best Practices\n\n- Use smaller models (like `ai\u002Fsmollm2`) for faster responses during development\n- Pre-load models with `--detach` for better performance in scripts\n- Models stay loaded until another model is requested or timeout (5 min)\n- Use the OpenAI-compatible API for integration with existing tools\n\n## References\n\nSee [references\u002Fdocker-model-guide.md](references\u002Fdocker-model-guide.md) for detailed documentation.\n",{"data":32,"body":33},{"name":4,"description":6},{"type":34,"children":35},"root",[36,43,49,56,61,251,257,262,414,419,516,522,665,671,709,715,728],{"type":37,"tag":38,"props":39,"children":40},"element","h1",{"id":4},[41],{"type":42,"value":28},"text",{"type":37,"tag":44,"props":45,"children":46},"p",{},[47],{"type":42,"value":48},"Docker Model Runner (DMR) makes it easy to run AI models locally using Docker. This skill helps you effectively use Docker Model Runner for local LLM inference in your development workflow.",{"type":37,"tag":50,"props":51,"children":53},"h2",{"id":52},"workflow",[54],{"type":42,"value":55},"Workflow",{"type":37,"tag":44,"props":57,"children":58},{},[59],{"type":42,"value":60},"When helping users with local LLM inference using Docker Model Runner:",{"type":37,"tag":62,"props":63,"children":64},"ol",{},[65,84,102,160,176,222],{"type":37,"tag":66,"props":67,"children":68},"li",{},[69,75,77],{"type":37,"tag":70,"props":71,"children":72},"strong",{},[73],{"type":42,"value":74},"Check if Docker Model Runner is available",{"type":42,"value":76}," by running ",{"type":37,"tag":78,"props":79,"children":81},"code",{"className":80},[],[82],{"type":42,"value":83},"docker model version",{"type":37,"tag":66,"props":85,"children":86},{},[87,92,94,100],{"type":37,"tag":70,"props":88,"children":89},{},[90],{"type":42,"value":91},"List available models",{"type":42,"value":93}," with ",{"type":37,"tag":78,"props":95,"children":97},{"className":96},[],[98],{"type":42,"value":99},"docker model list",{"type":42,"value":101}," to see what's already pulled",{"type":37,"tag":66,"props":103,"children":104},{},[105,110,112],{"type":37,"tag":70,"props":106,"children":107},{},[108],{"type":42,"value":109},"Search for models",{"type":42,"value":111}," on Docker Hub or HuggingFace:",{"type":37,"tag":113,"props":114,"children":115},"ul",{},[116,127],{"type":37,"tag":66,"props":117,"children":118},{},[119,125],{"type":37,"tag":78,"props":120,"children":122},{"className":121},[],[123],{"type":42,"value":124},"docker model search \u003Cquery>",{"type":42,"value":126}," to find models",{"type":37,"tag":66,"props":128,"children":129},{},[130,132,138,140,146,147,153,154],{"type":42,"value":131},"Popular models include: ",{"type":37,"tag":78,"props":133,"children":135},{"className":134},[],[136],{"type":42,"value":137},"ai\u002Fgemma3",{"type":42,"value":139},", ",{"type":37,"tag":78,"props":141,"children":143},{"className":142},[],[144],{"type":42,"value":145},"ai\u002Fllama3.2",{"type":42,"value":139},{"type":37,"tag":78,"props":148,"children":150},{"className":149},[],[151],{"type":42,"value":152},"ai\u002Fsmollm2",{"type":42,"value":139},{"type":37,"tag":78,"props":155,"children":157},{"className":156},[],[158],{"type":42,"value":159},"ai\u002Fqwen3",{"type":37,"tag":66,"props":161,"children":162},{},[163,168,170],{"type":37,"tag":70,"props":164,"children":165},{},[166],{"type":42,"value":167},"Pull models",{"type":42,"value":169}," before running: ",{"type":37,"tag":78,"props":171,"children":173},{"className":172},[],[174],{"type":42,"value":175},"docker model pull \u003Cmodel>",{"type":37,"tag":66,"props":177,"children":178},{},[179,184,186],{"type":37,"tag":70,"props":180,"children":181},{},[182],{"type":42,"value":183},"Run models",{"type":42,"value":185}," for inference:",{"type":37,"tag":113,"props":187,"children":188},{},[189,200,211],{"type":37,"tag":66,"props":190,"children":191},{},[192,194],{"type":42,"value":193},"One-time prompt: ",{"type":37,"tag":78,"props":195,"children":197},{"className":196},[],[198],{"type":42,"value":199},"docker model run ai\u002Fsmollm2 \"Your prompt here\"",{"type":37,"tag":66,"props":201,"children":202},{},[203,205],{"type":42,"value":204},"Interactive chat: ",{"type":37,"tag":78,"props":206,"children":208},{"className":207},[],[209],{"type":42,"value":210},"docker model run ai\u002Fsmollm2",{"type":37,"tag":66,"props":212,"children":213},{},[214,216],{"type":42,"value":215},"Pre-load model: ",{"type":37,"tag":78,"props":217,"children":219},{"className":218},[],[220],{"type":42,"value":221},"docker model run --detach ai\u002Fsmollm2",{"type":37,"tag":66,"props":223,"children":224},{},[225,230,232],{"type":37,"tag":70,"props":226,"children":227},{},[228],{"type":42,"value":229},"Use the OpenAI-compatible API",{"type":42,"value":231}," for programmatic access:",{"type":37,"tag":113,"props":233,"children":234},{},[235,246],{"type":37,"tag":66,"props":236,"children":237},{},[238,240],{"type":42,"value":239},"Endpoint: ",{"type":37,"tag":78,"props":241,"children":243},{"className":242},[],[244],{"type":42,"value":245},"http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\u002Fchat\u002Fcompletions",{"type":37,"tag":66,"props":247,"children":248},{},[249],{"type":42,"value":250},"This is compatible with OpenAI client libraries",{"type":37,"tag":50,"props":252,"children":254},{"id":253},"api-usage",[255],{"type":42,"value":256},"API Usage",{"type":37,"tag":44,"props":258,"children":259},{},[260],{"type":42,"value":261},"Docker Model Runner exposes an OpenAI-compatible REST API:",{"type":37,"tag":263,"props":264,"children":269},"pre",{"className":265,"code":266,"language":267,"meta":268,"style":268},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Chat completions\ncurl http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"model\": \"ai\u002Fsmollm2\",\n    \"messages\": [\n      {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n      {\"role\": \"user\", \"content\": \"Hello!\"}\n    ]\n  }'\n","bash","",[270],{"type":37,"tag":78,"props":271,"children":272},{"__ignoreMap":268},[273,285,307,336,355,364,373,382,391,400],{"type":37,"tag":274,"props":275,"children":278},"span",{"class":276,"line":277},"line",1,[279],{"type":37,"tag":274,"props":280,"children":282},{"style":281},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[283],{"type":42,"value":284},"# Chat completions\n",{"type":37,"tag":274,"props":286,"children":288},{"class":276,"line":287},2,[289,295,301],{"type":37,"tag":274,"props":290,"children":292},{"style":291},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[293],{"type":42,"value":294},"curl",{"type":37,"tag":274,"props":296,"children":298},{"style":297},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[299],{"type":42,"value":300}," http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\u002Fchat\u002Fcompletions",{"type":37,"tag":274,"props":302,"children":304},{"style":303},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[305],{"type":42,"value":306}," \\\n",{"type":37,"tag":274,"props":308,"children":310},{"class":276,"line":309},3,[311,316,322,327,332],{"type":37,"tag":274,"props":312,"children":313},{"style":297},[314],{"type":42,"value":315},"  -H",{"type":37,"tag":274,"props":317,"children":319},{"style":318},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[320],{"type":42,"value":321}," \"",{"type":37,"tag":274,"props":323,"children":324},{"style":297},[325],{"type":42,"value":326},"Content-Type: application\u002Fjson",{"type":37,"tag":274,"props":328,"children":329},{"style":318},[330],{"type":42,"value":331},"\"",{"type":37,"tag":274,"props":333,"children":334},{"style":303},[335],{"type":42,"value":306},{"type":37,"tag":274,"props":337,"children":339},{"class":276,"line":338},4,[340,345,350],{"type":37,"tag":274,"props":341,"children":342},{"style":297},[343],{"type":42,"value":344},"  -d",{"type":37,"tag":274,"props":346,"children":347},{"style":318},[348],{"type":42,"value":349}," '",{"type":37,"tag":274,"props":351,"children":352},{"style":297},[353],{"type":42,"value":354},"{\n",{"type":37,"tag":274,"props":356,"children":358},{"class":276,"line":357},5,[359],{"type":37,"tag":274,"props":360,"children":361},{"style":297},[362],{"type":42,"value":363},"    \"model\": \"ai\u002Fsmollm2\",\n",{"type":37,"tag":274,"props":365,"children":367},{"class":276,"line":366},6,[368],{"type":37,"tag":274,"props":369,"children":370},{"style":297},[371],{"type":42,"value":372},"    \"messages\": [\n",{"type":37,"tag":274,"props":374,"children":376},{"class":276,"line":375},7,[377],{"type":37,"tag":274,"props":378,"children":379},{"style":297},[380],{"type":42,"value":381},"      {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",{"type":37,"tag":274,"props":383,"children":385},{"class":276,"line":384},8,[386],{"type":37,"tag":274,"props":387,"children":388},{"style":297},[389],{"type":42,"value":390},"      {\"role\": \"user\", \"content\": \"Hello!\"}\n",{"type":37,"tag":274,"props":392,"children":394},{"class":276,"line":393},9,[395],{"type":37,"tag":274,"props":396,"children":397},{"style":297},[398],{"type":42,"value":399},"    ]\n",{"type":37,"tag":274,"props":401,"children":403},{"class":276,"line":402},10,[404,409],{"type":37,"tag":274,"props":405,"children":406},{"style":297},[407],{"type":42,"value":408},"  }",{"type":37,"tag":274,"props":410,"children":411},{"style":318},[412],{"type":42,"value":413},"'\n",{"type":37,"tag":44,"props":415,"children":416},{},[417],{"type":42,"value":418},"For Python with the OpenAI library:",{"type":37,"tag":263,"props":420,"children":424},{"className":421,"code":422,"language":423,"meta":268,"style":268},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from openai import OpenAI\n\nclient = OpenAI(\n    base_url=\"http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\",\n    api_key=\"not-needed\"  # API key not required for local inference\n)\n\nresponse = client.chat.completions.create(\n    model=\"ai\u002Fsmollm2\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}]\n)\n","python",[425],{"type":37,"tag":78,"props":426,"children":427},{"__ignoreMap":268},[428,436,445,453,461,469,477,484,492,500,508],{"type":37,"tag":274,"props":429,"children":430},{"class":276,"line":277},[431],{"type":37,"tag":274,"props":432,"children":433},{},[434],{"type":42,"value":435},"from openai import OpenAI\n",{"type":37,"tag":274,"props":437,"children":438},{"class":276,"line":287},[439],{"type":37,"tag":274,"props":440,"children":442},{"emptyLinePlaceholder":441},true,[443],{"type":42,"value":444},"\n",{"type":37,"tag":274,"props":446,"children":447},{"class":276,"line":309},[448],{"type":37,"tag":274,"props":449,"children":450},{},[451],{"type":42,"value":452},"client = OpenAI(\n",{"type":37,"tag":274,"props":454,"children":455},{"class":276,"line":338},[456],{"type":37,"tag":274,"props":457,"children":458},{},[459],{"type":42,"value":460},"    base_url=\"http:\u002F\u002Flocalhost:12434\u002Fengines\u002Fllama.cpp\u002Fv1\",\n",{"type":37,"tag":274,"props":462,"children":463},{"class":276,"line":357},[464],{"type":37,"tag":274,"props":465,"children":466},{},[467],{"type":42,"value":468},"    api_key=\"not-needed\"  # API key not required for local inference\n",{"type":37,"tag":274,"props":470,"children":471},{"class":276,"line":366},[472],{"type":37,"tag":274,"props":473,"children":474},{},[475],{"type":42,"value":476},")\n",{"type":37,"tag":274,"props":478,"children":479},{"class":276,"line":375},[480],{"type":37,"tag":274,"props":481,"children":482},{"emptyLinePlaceholder":441},[483],{"type":42,"value":444},{"type":37,"tag":274,"props":485,"children":486},{"class":276,"line":384},[487],{"type":37,"tag":274,"props":488,"children":489},{},[490],{"type":42,"value":491},"response = client.chat.completions.create(\n",{"type":37,"tag":274,"props":493,"children":494},{"class":276,"line":393},[495],{"type":37,"tag":274,"props":496,"children":497},{},[498],{"type":42,"value":499},"    model=\"ai\u002Fsmollm2\",\n",{"type":37,"tag":274,"props":501,"children":502},{"class":276,"line":402},[503],{"type":37,"tag":274,"props":504,"children":505},{},[506],{"type":42,"value":507},"    messages=[{\"role\": \"user\", \"content\": \"Hello!\"}]\n",{"type":37,"tag":274,"props":509,"children":511},{"class":276,"line":510},11,[512],{"type":37,"tag":274,"props":513,"children":514},{},[515],{"type":42,"value":476},{"type":37,"tag":50,"props":517,"children":519},{"id":518},"key-commands",[520],{"type":42,"value":521},"Key Commands",{"type":37,"tag":523,"props":524,"children":525},"table",{},[526,545],{"type":37,"tag":527,"props":528,"children":529},"thead",{},[530],{"type":37,"tag":531,"props":532,"children":533},"tr",{},[534,540],{"type":37,"tag":535,"props":536,"children":537},"th",{},[538],{"type":42,"value":539},"Command",{"type":37,"tag":535,"props":541,"children":542},{},[543],{"type":42,"value":544},"Description",{"type":37,"tag":546,"props":547,"children":548},"tbody",{},[549,567,583,599,614,631,648],{"type":37,"tag":531,"props":550,"children":551},{},[552,562],{"type":37,"tag":553,"props":554,"children":555},"td",{},[556],{"type":37,"tag":78,"props":557,"children":559},{"className":558},[],[560],{"type":42,"value":561},"docker model run \u003Cmodel> [prompt]",{"type":37,"tag":553,"props":563,"children":564},{},[565],{"type":42,"value":566},"Run a model with optional prompt",{"type":37,"tag":531,"props":568,"children":569},{},[570,578],{"type":37,"tag":553,"props":571,"children":572},{},[573],{"type":37,"tag":78,"props":574,"children":576},{"className":575},[],[577],{"type":42,"value":175},{"type":37,"tag":553,"props":579,"children":580},{},[581],{"type":42,"value":582},"Pull a model from registry",{"type":37,"tag":531,"props":584,"children":585},{},[586,594],{"type":37,"tag":553,"props":587,"children":588},{},[589],{"type":37,"tag":78,"props":590,"children":592},{"className":591},[],[593],{"type":42,"value":99},{"type":37,"tag":553,"props":595,"children":596},{},[597],{"type":42,"value":598},"List downloaded models",{"type":37,"tag":531,"props":600,"children":601},{},[602,610],{"type":37,"tag":553,"props":603,"children":604},{},[605],{"type":37,"tag":78,"props":606,"children":608},{"className":607},[],[609],{"type":42,"value":124},{"type":37,"tag":553,"props":611,"children":612},{},[613],{"type":42,"value":109},{"type":37,"tag":531,"props":615,"children":616},{},[617,626],{"type":37,"tag":553,"props":618,"children":619},{},[620],{"type":37,"tag":78,"props":621,"children":623},{"className":622},[],[624],{"type":42,"value":625},"docker model ps",{"type":37,"tag":553,"props":627,"children":628},{},[629],{"type":42,"value":630},"Show running models",{"type":37,"tag":531,"props":632,"children":633},{},[634,643],{"type":37,"tag":553,"props":635,"children":636},{},[637],{"type":37,"tag":78,"props":638,"children":640},{"className":639},[],[641],{"type":42,"value":642},"docker model rm \u003Cmodel>",{"type":37,"tag":553,"props":644,"children":645},{},[646],{"type":42,"value":647},"Remove a model",{"type":37,"tag":531,"props":649,"children":650},{},[651,660],{"type":37,"tag":553,"props":652,"children":653},{},[654],{"type":37,"tag":78,"props":655,"children":657},{"className":656},[],[658],{"type":42,"value":659},"docker model inspect \u003Cmodel>",{"type":37,"tag":553,"props":661,"children":662},{},[663],{"type":42,"value":664},"Show model details",{"type":37,"tag":50,"props":666,"children":668},{"id":667},"best-practices",[669],{"type":42,"value":670},"Best Practices",{"type":37,"tag":113,"props":672,"children":673},{},[674,686,699,704],{"type":37,"tag":66,"props":675,"children":676},{},[677,679,684],{"type":42,"value":678},"Use smaller models (like ",{"type":37,"tag":78,"props":680,"children":682},{"className":681},[],[683],{"type":42,"value":152},{"type":42,"value":685},") for faster responses during development",{"type":37,"tag":66,"props":687,"children":688},{},[689,691,697],{"type":42,"value":690},"Pre-load models with ",{"type":37,"tag":78,"props":692,"children":694},{"className":693},[],[695],{"type":42,"value":696},"--detach",{"type":42,"value":698}," for better performance in scripts",{"type":37,"tag":66,"props":700,"children":701},{},[702],{"type":42,"value":703},"Models stay loaded until another model is requested or timeout (5 min)",{"type":37,"tag":66,"props":705,"children":706},{},[707],{"type":42,"value":708},"Use the OpenAI-compatible API for integration with existing tools",{"type":37,"tag":50,"props":710,"children":712},{"id":711},"references",[713],{"type":42,"value":714},"References",{"type":37,"tag":44,"props":716,"children":717},{},[718,720,726],{"type":42,"value":719},"See ",{"type":37,"tag":721,"props":722,"children":724},"a",{"href":723},"references\u002Fdocker-model-guide.md",[725],{"type":42,"value":723},{"type":42,"value":727}," for detailed documentation.",{"type":37,"tag":729,"props":730,"children":731},"style",{},[732],{"type":42,"value":733},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":735,"total":309},[736,742,764],{"slug":4,"name":4,"fn":5,"description":6,"org":737,"tags":738,"stars":20,"repoUrl":21,"updatedAt":22},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[739,740,741],{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":743,"name":743,"fn":744,"description":745,"org":746,"tags":747,"stars":761,"repoUrl":762,"updatedAt":763},"kit-author","author Docker sandbox kits","Author Docker Sandboxes kits (agents and mixins) — spec.yaml schema, full lifecycle from sourcing through composition, injection, and runtime, plus distribution and TCK testing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[748,751,752,755,758],{"name":749,"slug":750,"type":15},"Architecture","architecture",{"name":9,"slug":8,"type":15},{"name":753,"slug":754,"type":15},"Engineering","engineering",{"name":756,"slug":757,"type":15},"Sandboxing","sandboxing",{"name":759,"slug":760,"type":15},"Testing","testing",67,"https:\u002F\u002Fgithub.com\u002Fdocker\u002Fsbx-kits-contrib","2026-07-19T05:39:37.670879",{"slug":765,"name":765,"fn":766,"description":767,"org":768,"tags":769,"stars":780,"repoUrl":781,"updatedAt":782},"mcp-server-yaml-creator","configure custom MCP servers in Docker","Add and configure custom MCP servers in Docker MCP Gateway. Use when users want to: (1) Integrate their own MCP server into the gateway, (2) Add new servers to catalogs or profiles, (3) Set up server authentication, networking, and configuration, (4) Understand MCP server integration requirements.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[770,773,776,777],{"name":771,"slug":772,"type":15},"Automation","automation",{"name":774,"slug":775,"type":15},"Configuration","configuration",{"name":9,"slug":8,"type":15},{"name":778,"slug":779,"type":15},"MCP","mcp",17,"https:\u002F\u002Fgithub.com\u002Fdocker\u002Fclaude-plugins","2026-07-12T08:15:15.779117",{"items":784,"total":277},[785],{"slug":4,"name":4,"fn":5,"description":6,"org":786,"tags":787,"stars":20,"repoUrl":21,"updatedAt":22},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[788,789,790],{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15}]