[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-cuopt-sandbox":3,"mdc-86f3wj-key":43,"related-org-nvidia-cuopt-sandbox":744,"related-repo-nvidia-cuopt-sandbox":904},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":38,"sourceUrl":41,"mdContent":42},"cuopt-sandbox","run cuOpt optimization in NemoClaw sandbox","Run cuOpt in the NemoClaw sandbox — probe\u002Fsmoke gates, prefer cancelable Python gRPC jobs, use legacy remote execution only when that API is unavailable, then vendored cuOpt skills.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,16,19,20],{"name":13,"slug":14,"type":15},"CLI","cli","tag",{"name":17,"slug":18,"type":15},"Optimization","optimization",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Simulation","simulation",462,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fcuopt-examples","2026-07-30T05:29:17.131364","Apache-2.0",81,[29,30,31,32,33,18,34,35,36,37],"combinatorial-optimization","gpu","linear-programming","mixed-integer-programming","operations-research","optimization-algorithms","route-optimization","traveling-salesman-problem","vehicle-routing-problem",{"repoUrl":24,"stars":23,"forks":27,"topics":39,"description":40},[29,30,31,32,33,18,34,35,36,37],"NVIDIA cuOpt examples for decision optimization","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fcuopt-examples\u002Ftree\u002FHEAD\u002Fcuopt_on_nemoclaw\u002Fopenclaw-skills\u002Fcuopt-sandbox","---\nname: cuopt-sandbox\nversion: \"26.08.00\"\ndescription: Run cuOpt in the NemoClaw sandbox — probe\u002Fsmoke gates, prefer cancelable Python gRPC jobs, use legacy remote execution only when that API is unavailable, then vendored cuOpt skills.\nlicense: Apache-2.0\nmetadata:\n  author: NVIDIA cuOpt Team\n  tags:\n    - cuopt\n    - nemoclaw\n    - sandbox\n---\n\n# cuOpt in the NemoClaw sandbox\n\nInfrastructure for solving with cuOpt inside NemoClaw: probe\u002Fsmoke gates,\ncapability-based gRPC execution, and handoff to vendored formulation\u002FAPI skills.\n\n## When to use\n\n- Constructive planning from uploaded constraint data (schedule, assign,\n  route, roster — any wording). See `references\u002Fintent-and-triggers.md`.\n- CSV upload + plan → `optimization-from-data-orchestrator` + `references\u002Factivation.md`.\n- `ImportError` \u002F `cudaErrorInsufficientDriver`.\n\n## Mandatory order\n\nComplete before any assignment output, feasibility verdict, or custom\nsolver code:\n\n| Step | Action | Reference |\n|---|---|---|\n| 0 | Probe capability → gRPC smoke | `references\u002Fgrpc-connectivity-and-smoke.md` |\n| 1 | Formulate | vendored `*-formulation` skills |\n| 2 | Solve (one job, terminal status) | `references\u002Flong-running-jobs.md` |\n\nInspecting uploaded data for columns and constraints is fine; emit a\ncompleted plan only after smoke succeeds.\n\n## Quick reference\n\n**Imports (LP\u002FMILP\u002FQP):**\n\n```python\nfrom cuopt.linear_programming.problem import Problem, INTEGER, MINIMIZE\nfrom cuopt.linear_programming.solver_settings import SolverSettings\n# When available (preferred):\nfrom cuopt.grpc.linear_programming import Client, GrpcError, JobStatus\n```\n\n**Interfaces:** LP\u002FMILP\u002FQP → prefer async Python gRPC client on `:5001`,\notherwise use the legacy remote fallback; routing → REST `:5000`. See\n`references\u002Fasync-grpc-python.md`, `references\u002Fremote-execution-fallback.md`,\n`references\u002Finterfaces.md`, and `references\u002Frouting-rest-only.md`.\n\n## Reference index\n\n| Topic | File |\n|---|---|\n| Activation \u002F skill order | `references\u002Factivation.md` |\n| Intent \u002F paraphrases | `references\u002Fintent-and-triggers.md` |\n| Gates \u002F common mistakes | `references\u002Fgates-and-first-actions.md` |\n| Async Python gRPC jobs | `references\u002Fasync-grpc-python.md` |\n| Legacy remote fallback | `references\u002Fremote-execution-fallback.md` |\n| Connectivity + smoke | `references\u002Fgrpc-connectivity-and-smoke.md` |\n| Python imports | `references\u002Fpython-imports.md` |\n| gRPC vs REST | `references\u002Finterfaces.md` |\n| Routing REST | `references\u002Frouting-rest-only.md` |\n| Paths + probe | `references\u002Fenvironment-and-networking.md` |\n| Long-running jobs | `references\u002Flong-running-jobs.md` |\n| Troubleshooting | `references\u002Ftroubleshooting.md` |\n\n## Orchestration skills (local)\n\nAfter gates: `optimization-from-data-orchestrator` → `optimization-intent-router`\n→ `tabular-optimization-ingestion` → `cuopt-model-mapper` (and\n`optimization-mode-router` when replay\u002Faudit signals appear).\n\n## Vendored upstream skills\n\nInstalled under `\u002Fsandbox\u002F.openclaw\u002Fskills\u002F` by `install-skill`:\n`numerical-optimization-formulation`, `cuopt-numerical-optimization-api-python`,\n`routing-formulation`, `cuopt-routing-api-python`, `cuopt-server-api-python`,\n`cuopt-user-rules`, etc.\n\nFor LP\u002FMILP\u002FQP, use upstream skills to build the model. Execute with this\nskill's async `Client` lifecycle when importable; only then fall back to the\nlegacy remote `Problem.solve()` path, which cannot cancel submitted work.\n",{"data":44,"body":52},{"name":4,"version":45,"description":6,"license":26,"metadata":46},"26.08.00",{"author":47,"tags":48},"NVIDIA cuOpt Team",[49,50,51],"cuopt","nemoclaw","sandbox",{"type":53,"children":54},"root",[55,64,70,77,134,140,145,248,253,259,268,317,374,380,598,604,647,653,717,738],{"type":56,"tag":57,"props":58,"children":60},"element","h1",{"id":59},"cuopt-in-the-nemoclaw-sandbox",[61],{"type":62,"value":63},"text","cuOpt in the NemoClaw sandbox",{"type":56,"tag":65,"props":66,"children":67},"p",{},[68],{"type":62,"value":69},"Infrastructure for solving with cuOpt inside NemoClaw: probe\u002Fsmoke gates,\ncapability-based gRPC execution, and handoff to vendored formulation\u002FAPI skills.",{"type":56,"tag":71,"props":72,"children":74},"h2",{"id":73},"when-to-use",[75],{"type":62,"value":76},"When to use",{"type":56,"tag":78,"props":79,"children":80},"ul",{},[81,96,116],{"type":56,"tag":82,"props":83,"children":84},"li",{},[85,87,94],{"type":62,"value":86},"Constructive planning from uploaded constraint data (schedule, assign,\nroute, roster — any wording). See ",{"type":56,"tag":88,"props":89,"children":91},"code",{"className":90},[],[92],{"type":62,"value":93},"references\u002Fintent-and-triggers.md",{"type":62,"value":95},".",{"type":56,"tag":82,"props":97,"children":98},{},[99,101,107,109,115],{"type":62,"value":100},"CSV upload + plan → ",{"type":56,"tag":88,"props":102,"children":104},{"className":103},[],[105],{"type":62,"value":106},"optimization-from-data-orchestrator",{"type":62,"value":108}," + ",{"type":56,"tag":88,"props":110,"children":112},{"className":111},[],[113],{"type":62,"value":114},"references\u002Factivation.md",{"type":62,"value":95},{"type":56,"tag":82,"props":117,"children":118},{},[119,125,127,133],{"type":56,"tag":88,"props":120,"children":122},{"className":121},[],[123],{"type":62,"value":124},"ImportError",{"type":62,"value":126}," \u002F ",{"type":56,"tag":88,"props":128,"children":130},{"className":129},[],[131],{"type":62,"value":132},"cudaErrorInsufficientDriver",{"type":62,"value":95},{"type":56,"tag":71,"props":135,"children":137},{"id":136},"mandatory-order",[138],{"type":62,"value":139},"Mandatory order",{"type":56,"tag":65,"props":141,"children":142},{},[143],{"type":62,"value":144},"Complete before any assignment output, feasibility verdict, or custom\nsolver code:",{"type":56,"tag":146,"props":147,"children":148},"table",{},[149,173],{"type":56,"tag":150,"props":151,"children":152},"thead",{},[153],{"type":56,"tag":154,"props":155,"children":156},"tr",{},[157,163,168],{"type":56,"tag":158,"props":159,"children":160},"th",{},[161],{"type":62,"value":162},"Step",{"type":56,"tag":158,"props":164,"children":165},{},[166],{"type":62,"value":167},"Action",{"type":56,"tag":158,"props":169,"children":170},{},[171],{"type":62,"value":172},"Reference",{"type":56,"tag":174,"props":175,"children":176},"tbody",{},[177,200,226],{"type":56,"tag":154,"props":178,"children":179},{},[180,186,191],{"type":56,"tag":181,"props":182,"children":183},"td",{},[184],{"type":62,"value":185},"0",{"type":56,"tag":181,"props":187,"children":188},{},[189],{"type":62,"value":190},"Probe capability → gRPC smoke",{"type":56,"tag":181,"props":192,"children":193},{},[194],{"type":56,"tag":88,"props":195,"children":197},{"className":196},[],[198],{"type":62,"value":199},"references\u002Fgrpc-connectivity-and-smoke.md",{"type":56,"tag":154,"props":201,"children":202},{},[203,208,213],{"type":56,"tag":181,"props":204,"children":205},{},[206],{"type":62,"value":207},"1",{"type":56,"tag":181,"props":209,"children":210},{},[211],{"type":62,"value":212},"Formulate",{"type":56,"tag":181,"props":214,"children":215},{},[216,218,224],{"type":62,"value":217},"vendored ",{"type":56,"tag":88,"props":219,"children":221},{"className":220},[],[222],{"type":62,"value":223},"*-formulation",{"type":62,"value":225}," skills",{"type":56,"tag":154,"props":227,"children":228},{},[229,234,239],{"type":56,"tag":181,"props":230,"children":231},{},[232],{"type":62,"value":233},"2",{"type":56,"tag":181,"props":235,"children":236},{},[237],{"type":62,"value":238},"Solve (one job, terminal status)",{"type":56,"tag":181,"props":240,"children":241},{},[242],{"type":56,"tag":88,"props":243,"children":245},{"className":244},[],[246],{"type":62,"value":247},"references\u002Flong-running-jobs.md",{"type":56,"tag":65,"props":249,"children":250},{},[251],{"type":62,"value":252},"Inspecting uploaded data for columns and constraints is fine; emit a\ncompleted plan only after smoke succeeds.",{"type":56,"tag":71,"props":254,"children":256},{"id":255},"quick-reference",[257],{"type":62,"value":258},"Quick reference",{"type":56,"tag":65,"props":260,"children":261},{},[262],{"type":56,"tag":263,"props":264,"children":265},"strong",{},[266],{"type":62,"value":267},"Imports (LP\u002FMILP\u002FQP):",{"type":56,"tag":269,"props":270,"children":275},"pre",{"className":271,"code":272,"language":273,"meta":274,"style":274},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from cuopt.linear_programming.problem import Problem, INTEGER, MINIMIZE\nfrom cuopt.linear_programming.solver_settings import SolverSettings\n# When available (preferred):\nfrom cuopt.grpc.linear_programming import Client, GrpcError, JobStatus\n","python","",[276],{"type":56,"tag":88,"props":277,"children":278},{"__ignoreMap":274},[279,290,299,308],{"type":56,"tag":280,"props":281,"children":284},"span",{"class":282,"line":283},"line",1,[285],{"type":56,"tag":280,"props":286,"children":287},{},[288],{"type":62,"value":289},"from cuopt.linear_programming.problem import Problem, INTEGER, MINIMIZE\n",{"type":56,"tag":280,"props":291,"children":293},{"class":282,"line":292},2,[294],{"type":56,"tag":280,"props":295,"children":296},{},[297],{"type":62,"value":298},"from cuopt.linear_programming.solver_settings import SolverSettings\n",{"type":56,"tag":280,"props":300,"children":302},{"class":282,"line":301},3,[303],{"type":56,"tag":280,"props":304,"children":305},{},[306],{"type":62,"value":307},"# When available (preferred):\n",{"type":56,"tag":280,"props":309,"children":311},{"class":282,"line":310},4,[312],{"type":56,"tag":280,"props":313,"children":314},{},[315],{"type":62,"value":316},"from cuopt.grpc.linear_programming import Client, GrpcError, JobStatus\n",{"type":56,"tag":65,"props":318,"children":319},{},[320,325,327,333,335,341,343,349,351,357,359,365,367,373],{"type":56,"tag":263,"props":321,"children":322},{},[323],{"type":62,"value":324},"Interfaces:",{"type":62,"value":326}," LP\u002FMILP\u002FQP → prefer async Python gRPC client on ",{"type":56,"tag":88,"props":328,"children":330},{"className":329},[],[331],{"type":62,"value":332},":5001",{"type":62,"value":334},",\notherwise use the legacy remote fallback; routing → REST ",{"type":56,"tag":88,"props":336,"children":338},{"className":337},[],[339],{"type":62,"value":340},":5000",{"type":62,"value":342},". See\n",{"type":56,"tag":88,"props":344,"children":346},{"className":345},[],[347],{"type":62,"value":348},"references\u002Fasync-grpc-python.md",{"type":62,"value":350},", ",{"type":56,"tag":88,"props":352,"children":354},{"className":353},[],[355],{"type":62,"value":356},"references\u002Fremote-execution-fallback.md",{"type":62,"value":358},",\n",{"type":56,"tag":88,"props":360,"children":362},{"className":361},[],[363],{"type":62,"value":364},"references\u002Finterfaces.md",{"type":62,"value":366},", and ",{"type":56,"tag":88,"props":368,"children":370},{"className":369},[],[371],{"type":62,"value":372},"references\u002Frouting-rest-only.md",{"type":62,"value":95},{"type":56,"tag":71,"props":375,"children":377},{"id":376},"reference-index",[378],{"type":62,"value":379},"Reference index",{"type":56,"tag":146,"props":381,"children":382},{},[383,399],{"type":56,"tag":150,"props":384,"children":385},{},[386],{"type":56,"tag":154,"props":387,"children":388},{},[389,394],{"type":56,"tag":158,"props":390,"children":391},{},[392],{"type":62,"value":393},"Topic",{"type":56,"tag":158,"props":395,"children":396},{},[397],{"type":62,"value":398},"File",{"type":56,"tag":174,"props":400,"children":401},{},[402,418,434,451,467,483,499,516,532,548,565,581],{"type":56,"tag":154,"props":403,"children":404},{},[405,410],{"type":56,"tag":181,"props":406,"children":407},{},[408],{"type":62,"value":409},"Activation \u002F skill order",{"type":56,"tag":181,"props":411,"children":412},{},[413],{"type":56,"tag":88,"props":414,"children":416},{"className":415},[],[417],{"type":62,"value":114},{"type":56,"tag":154,"props":419,"children":420},{},[421,426],{"type":56,"tag":181,"props":422,"children":423},{},[424],{"type":62,"value":425},"Intent \u002F paraphrases",{"type":56,"tag":181,"props":427,"children":428},{},[429],{"type":56,"tag":88,"props":430,"children":432},{"className":431},[],[433],{"type":62,"value":93},{"type":56,"tag":154,"props":435,"children":436},{},[437,442],{"type":56,"tag":181,"props":438,"children":439},{},[440],{"type":62,"value":441},"Gates \u002F common mistakes",{"type":56,"tag":181,"props":443,"children":444},{},[445],{"type":56,"tag":88,"props":446,"children":448},{"className":447},[],[449],{"type":62,"value":450},"references\u002Fgates-and-first-actions.md",{"type":56,"tag":154,"props":452,"children":453},{},[454,459],{"type":56,"tag":181,"props":455,"children":456},{},[457],{"type":62,"value":458},"Async Python gRPC jobs",{"type":56,"tag":181,"props":460,"children":461},{},[462],{"type":56,"tag":88,"props":463,"children":465},{"className":464},[],[466],{"type":62,"value":348},{"type":56,"tag":154,"props":468,"children":469},{},[470,475],{"type":56,"tag":181,"props":471,"children":472},{},[473],{"type":62,"value":474},"Legacy remote fallback",{"type":56,"tag":181,"props":476,"children":477},{},[478],{"type":56,"tag":88,"props":479,"children":481},{"className":480},[],[482],{"type":62,"value":356},{"type":56,"tag":154,"props":484,"children":485},{},[486,491],{"type":56,"tag":181,"props":487,"children":488},{},[489],{"type":62,"value":490},"Connectivity + smoke",{"type":56,"tag":181,"props":492,"children":493},{},[494],{"type":56,"tag":88,"props":495,"children":497},{"className":496},[],[498],{"type":62,"value":199},{"type":56,"tag":154,"props":500,"children":501},{},[502,507],{"type":56,"tag":181,"props":503,"children":504},{},[505],{"type":62,"value":506},"Python imports",{"type":56,"tag":181,"props":508,"children":509},{},[510],{"type":56,"tag":88,"props":511,"children":513},{"className":512},[],[514],{"type":62,"value":515},"references\u002Fpython-imports.md",{"type":56,"tag":154,"props":517,"children":518},{},[519,524],{"type":56,"tag":181,"props":520,"children":521},{},[522],{"type":62,"value":523},"gRPC vs REST",{"type":56,"tag":181,"props":525,"children":526},{},[527],{"type":56,"tag":88,"props":528,"children":530},{"className":529},[],[531],{"type":62,"value":364},{"type":56,"tag":154,"props":533,"children":534},{},[535,540],{"type":56,"tag":181,"props":536,"children":537},{},[538],{"type":62,"value":539},"Routing REST",{"type":56,"tag":181,"props":541,"children":542},{},[543],{"type":56,"tag":88,"props":544,"children":546},{"className":545},[],[547],{"type":62,"value":372},{"type":56,"tag":154,"props":549,"children":550},{},[551,556],{"type":56,"tag":181,"props":552,"children":553},{},[554],{"type":62,"value":555},"Paths + probe",{"type":56,"tag":181,"props":557,"children":558},{},[559],{"type":56,"tag":88,"props":560,"children":562},{"className":561},[],[563],{"type":62,"value":564},"references\u002Fenvironment-and-networking.md",{"type":56,"tag":154,"props":566,"children":567},{},[568,573],{"type":56,"tag":181,"props":569,"children":570},{},[571],{"type":62,"value":572},"Long-running jobs",{"type":56,"tag":181,"props":574,"children":575},{},[576],{"type":56,"tag":88,"props":577,"children":579},{"className":578},[],[580],{"type":62,"value":247},{"type":56,"tag":154,"props":582,"children":583},{},[584,589],{"type":56,"tag":181,"props":585,"children":586},{},[587],{"type":62,"value":588},"Troubleshooting",{"type":56,"tag":181,"props":590,"children":591},{},[592],{"type":56,"tag":88,"props":593,"children":595},{"className":594},[],[596],{"type":62,"value":597},"references\u002Ftroubleshooting.md",{"type":56,"tag":71,"props":599,"children":601},{"id":600},"orchestration-skills-local",[602],{"type":62,"value":603},"Orchestration skills (local)",{"type":56,"tag":65,"props":605,"children":606},{},[607,609,614,616,622,624,630,631,637,639,645],{"type":62,"value":608},"After gates: ",{"type":56,"tag":88,"props":610,"children":612},{"className":611},[],[613],{"type":62,"value":106},{"type":62,"value":615}," → ",{"type":56,"tag":88,"props":617,"children":619},{"className":618},[],[620],{"type":62,"value":621},"optimization-intent-router",{"type":62,"value":623},"\n→ ",{"type":56,"tag":88,"props":625,"children":627},{"className":626},[],[628],{"type":62,"value":629},"tabular-optimization-ingestion",{"type":62,"value":615},{"type":56,"tag":88,"props":632,"children":634},{"className":633},[],[635],{"type":62,"value":636},"cuopt-model-mapper",{"type":62,"value":638}," (and\n",{"type":56,"tag":88,"props":640,"children":642},{"className":641},[],[643],{"type":62,"value":644},"optimization-mode-router",{"type":62,"value":646}," when replay\u002Faudit signals appear).",{"type":56,"tag":71,"props":648,"children":650},{"id":649},"vendored-upstream-skills",[651],{"type":62,"value":652},"Vendored upstream skills",{"type":56,"tag":65,"props":654,"children":655},{},[656,658,664,666,672,674,680,681,687,688,694,695,701,702,708,709,715],{"type":62,"value":657},"Installed under ",{"type":56,"tag":88,"props":659,"children":661},{"className":660},[],[662],{"type":62,"value":663},"\u002Fsandbox\u002F.openclaw\u002Fskills\u002F",{"type":62,"value":665}," by ",{"type":56,"tag":88,"props":667,"children":669},{"className":668},[],[670],{"type":62,"value":671},"install-skill",{"type":62,"value":673},":\n",{"type":56,"tag":88,"props":675,"children":677},{"className":676},[],[678],{"type":62,"value":679},"numerical-optimization-formulation",{"type":62,"value":350},{"type":56,"tag":88,"props":682,"children":684},{"className":683},[],[685],{"type":62,"value":686},"cuopt-numerical-optimization-api-python",{"type":62,"value":358},{"type":56,"tag":88,"props":689,"children":691},{"className":690},[],[692],{"type":62,"value":693},"routing-formulation",{"type":62,"value":350},{"type":56,"tag":88,"props":696,"children":698},{"className":697},[],[699],{"type":62,"value":700},"cuopt-routing-api-python",{"type":62,"value":350},{"type":56,"tag":88,"props":703,"children":705},{"className":704},[],[706],{"type":62,"value":707},"cuopt-server-api-python",{"type":62,"value":358},{"type":56,"tag":88,"props":710,"children":712},{"className":711},[],[713],{"type":62,"value":714},"cuopt-user-rules",{"type":62,"value":716},", etc.",{"type":56,"tag":65,"props":718,"children":719},{},[720,722,728,730,736],{"type":62,"value":721},"For LP\u002FMILP\u002FQP, use upstream skills to build the model. Execute with this\nskill's async ",{"type":56,"tag":88,"props":723,"children":725},{"className":724},[],[726],{"type":62,"value":727},"Client",{"type":62,"value":729}," lifecycle when importable; only then fall back to the\nlegacy remote ",{"type":56,"tag":88,"props":731,"children":733},{"className":732},[],[734],{"type":62,"value":735},"Problem.solve()",{"type":62,"value":737}," path, which cannot cancel submitted work.",{"type":56,"tag":739,"props":740,"children":741},"style",{},[742],{"type":62,"value":743},"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":745,"total":903},[746,764,781,792,804,818,831,845,858,869,883,892],{"slug":747,"name":747,"fn":748,"description":749,"org":750,"tags":751,"stars":761,"repoUrl":762,"updatedAt":763},"nemoclaw-user-guide","retrieve NemoClaw documentation and configuration","Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[752,755,758],{"name":753,"slug":754,"type":15},"Documentation","documentation",{"name":756,"slug":757,"type":15},"MCP","mcp",{"name":759,"slug":760,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":765,"name":765,"fn":766,"description":767,"org":768,"tags":769,"stars":778,"repoUrl":779,"updatedAt":780},"mcore-build-and-dependency","manage Megatron-LM development environments","Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and updating uv.lock.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[770,773,776],{"name":771,"slug":772,"type":15},"Containers","containers",{"name":774,"slug":775,"type":15},"Deployment","deployment",{"name":777,"slug":273,"type":15},"Python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":782,"name":782,"fn":783,"description":784,"org":785,"tags":786,"stars":778,"repoUrl":779,"updatedAt":791},"mcore-bump-base-image","update NVIDIA PyTorch base images","Bump the NVIDIA PyTorch base image (`nvcr.io\u002Fnvidia\u002Fpytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker\u002F.ngc_version.dev` and GitLab CI in `.gitlab\u002Fstages\u002F01.build.yml`), the post-bump CI loop (re-run functional tests, refresh golden values, mark broken tests), and the gotchas that bit PRs",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[787,790],{"name":788,"slug":789,"type":15},"CI\u002FCD","ci-cd",{"name":774,"slug":775,"type":15},"2026-07-14T05:25:59.97109",{"slug":793,"name":793,"fn":794,"description":795,"org":796,"tags":797,"stars":778,"repoUrl":779,"updatedAt":803},"mcore-cicd","manage CI\u002FCD pipelines for Megatron-LM","CI\u002FCD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a pull-request\u002FBRANCH ref — always dry-run and verify the destination first; never run against shared or protected branches), and CI failure investigation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[798,799,800],{"name":788,"slug":789,"type":15},{"name":774,"slug":775,"type":15},{"name":801,"slug":802,"type":15},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":805,"name":805,"fn":806,"description":807,"org":808,"tags":809,"stars":778,"repoUrl":779,"updatedAt":817},"mcore-create-issue","investigate CI failures and create issues","Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[810,813,814],{"name":811,"slug":812,"type":15},"Debugging","debugging",{"name":801,"slug":802,"type":15},{"name":815,"slug":816,"type":15},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":819,"name":819,"fn":820,"description":821,"org":822,"tags":823,"stars":778,"repoUrl":779,"updatedAt":830},"mcore-linting-and-formatting","lint and format Megatron-LM code","Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[824,827],{"name":825,"slug":826,"type":15},"Best Practices","best-practices",{"name":828,"slug":829,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":832,"name":832,"fn":833,"description":834,"org":835,"tags":836,"stars":778,"repoUrl":779,"updatedAt":844},"mcore-migrate-gpt-to-hybrid","migrate Megatron-LM models to HybridModel","Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[837,840,843],{"name":838,"slug":839,"type":15},"Machine Learning","machine-learning",{"name":841,"slug":842,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:11.777011",{"slug":846,"name":846,"fn":847,"description":848,"org":849,"tags":850,"stars":778,"repoUrl":779,"updatedAt":857},"mcore-onboard-gb200-1node-tests","onboard functional tests for GB200","Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[851,854],{"name":852,"slug":853,"type":15},"QA","qa",{"name":855,"slug":856,"type":15},"Testing","testing","2026-07-14T05:25:53.673039",{"slug":859,"name":859,"fn":860,"description":861,"org":862,"tags":863,"stars":778,"repoUrl":779,"updatedAt":868},"mcore-run-on-slurm","launch distributed training jobs on SLURM","How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[864,865],{"name":774,"slug":775,"type":15},{"name":866,"slug":867,"type":15},"Infrastructure","infrastructure","2026-07-14T05:25:49.362534",{"slug":870,"name":870,"fn":871,"description":872,"org":873,"tags":874,"stars":778,"repoUrl":779,"updatedAt":882},"mcore-split-pr","split pull requests to reduce review load","Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[875,878,879],{"name":876,"slug":877,"type":15},"Code Review","code-review",{"name":801,"slug":802,"type":15},{"name":880,"slug":881,"type":15},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":884,"name":884,"fn":885,"description":886,"org":887,"tags":888,"stars":778,"repoUrl":779,"updatedAt":891},"mcore-testing","run and manage Megatron-LM tests","Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[889,890],{"name":852,"slug":853,"type":15},{"name":855,"slug":856,"type":15},"2026-07-14T05:25:54.928983",{"slug":893,"name":893,"fn":894,"description":895,"org":896,"tags":897,"stars":778,"repoUrl":779,"updatedAt":902},"nightly-sync","manage nightly main-to-dev sync workflows","Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[898,901],{"name":899,"slug":900,"type":15},"Automation","automation",{"name":788,"slug":789,"type":15},"2026-07-30T05:29:03.275638",496,{"items":905,"total":985},[906,919,930,937,950,962,976],{"slug":907,"name":907,"fn":908,"description":909,"org":910,"tags":911,"stars":23,"repoUrl":24,"updatedAt":918},"cuopt-debugging","debug NVIDIA cuOpt optimization problems","Troubleshoot cuOpt LP\u002FMILP problems including errors, wrong results, infeasible solutions, performance issues, and status codes. Use when the user says something isn't working, gets unexpected results, or needs help diagnosing issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[912,913,916,917],{"name":811,"slug":812,"type":15},{"name":914,"slug":915,"type":15},"Mathematics","mathematics",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-23T05:43:32.51428",{"slug":636,"name":636,"fn":920,"description":921,"org":922,"tags":923,"stars":23,"repoUrl":24,"updatedAt":929},"map optimization problems to cuOpt models","Map interpreted optimization problems into cuOpt-native models for the fast path with minimal clarifying questions.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[924,927,928],{"name":925,"slug":926,"type":15},"Data Modeling","data-modeling",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-30T05:29:19.401656",{"slug":4,"name":4,"fn":5,"description":6,"org":931,"tags":932,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[933,934,935,936],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":21,"slug":22,"type":15},{"slug":938,"name":938,"fn":939,"description":940,"org":941,"tags":942,"stars":23,"repoUrl":24,"updatedAt":949},"generic-max-supply","plan supply chain models with cuOpt","Multi-period supply chain planning model: data files, BOM structure, variable\u002Fconstraint reference for the max-supply base model.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[943,944,945,946],{"name":925,"slug":926,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":947,"slug":948,"type":15},"Supply Chain","supply-chain","2026-07-14T05:32:29.39577",{"slug":106,"name":106,"fn":951,"description":952,"org":953,"tags":954,"stars":23,"repoUrl":24,"updatedAt":961},"orchestrate optimization data and solving","Coordinate uploaded data plus a natural-language question into interpretation, clarification, cuOpt solve, and a user-facing answer.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[955,956,959,960],{"name":899,"slug":900,"type":15},{"name":957,"slug":958,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-14T05:32:59.680482",{"slug":621,"name":621,"fn":963,"description":964,"org":965,"tags":966,"stars":23,"repoUrl":24,"updatedAt":975},"classify optimization and analytics requests","Classify whether a data-backed request is LP, MILP, QP, routing, or non-optimization analytics.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[967,970,973,974],{"name":968,"slug":969,"type":15},"Analytics","analytics",{"name":971,"slug":972,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-14T05:32:53.475243",{"slug":644,"name":644,"fn":977,"description":978,"org":979,"tags":980,"stars":23,"repoUrl":24,"updatedAt":984},"route optimization requests to cuOpt solvers","Choose fast direct-to-cuOpt solve versus replayable or auditable model artifact mode.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[981,982,983],{"name":899,"slug":900,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-07-30T05:29:18.162351",8]