[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-deep-research":3,"mdc--1zeki9-key":33,"related-repo-nvidia-deep-research":531,"related-org-nvidia-deep-research":635},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"deep-research","queue deep multi-step research tasks","Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.",{"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],{"name":13,"slug":14,"type":15},"Research","research","tag",{"name":17,"slug":18,"type":15},"Agents","agents",{"name":20,"slug":21,"type":15},"Multi-Agent","multi-agent",72,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fnemoclaw-community","2026-08-31T09:19:11.215563",null,32,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"Our repository of community driven examples, showcases, and integrations","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fnemoclaw-community\u002Ftree\u002FHEAD\u002Fexamples\u002Frecipes\u002Fcommunity\u002Fdeep-research-worker\u002Fsrc","---\nname: deep-research\ndescription: Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.\n---\n\n\u003C!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n# Deep Research\n\nDelegate complex, long-running research and multi-document analysis to the DeepAgents background worker service.\n\n## Routing Rule\nFor deep research, comprehensive analysis, or multi-step investigations, execute `\u002Fsandbox\u002Fbin\u002Fdeep-research`.\n\nDo not perform the same long-running task again inline after it has been delegated.\n\n## How To Use\n\n```bash\n\u002Fsandbox\u002Fbin\u002Fdeep-research [--depth shallow|standard|deep] [--rubric \"\u003Ccustom criteria>\"] \"\u003Cresearch prompt or goal>\"\n```\n\n### Examples\n\n**Standard Research (Default):**\n```bash\n\u002Fsandbox\u002Fbin\u002Fdeep-research \"Analysis of vector database performance benchmarks in 2026\"\n```\n\n**Deep Research:**\n```bash\n\u002Fsandbox\u002Fbin\u002Fdeep-research --depth deep \"Research the 5 levels of agentic workflow platform security and draft a technical whitepaper\"\n```\n\n**Custom Rubric Validation:**\n```bash\n\u002Fsandbox\u002Fbin\u002Fdeep-research --depth deep --rubric \"Compare the alternatives in a table and cite each major factual claim\" \"Compare public retrieval architectures\"\n```\n\n## Options & Arguments\n- `--depth \u003Cshallow|standard|deep>`: Execution depth preset:\n- `shallow`: 25 graph steps, 1 rubric iteration\n- `standard` (default): 50 graph steps, 2 rubric iterations\n- `deep`: 100 graph steps, 3 rubric iterations\n- `--rubric \"\u003Ctext>\"`: Optional custom quality rubric for `RubricMiddleware` cross-validation. If omitted, the worker creates a request-specific evidence rubric before invocation.\n- Position 1: The research prompt or goal (required string)\n\n## How It Works\n1. **Task Enqueued**: Submitted to the DeepAgents worker service via SQLite queue.\n2. **Planning**: The worker initializes `write_todos` and applies either the supplied rubric or a request-specific default rubric.\n3. **SubAgent Delegation**: Research subtopics are delegated to isolated `SubAgent` workers to prevent context window saturation.\n4. **Cross-Validation**: `RubricMiddleware` evaluates the output against the quality rubric, triggering iterative refinement loops if criteria are not met.\n5. **Output Delivered**: Formatted report is returned to stdout.\n\n## Execution Constraints\n- Up to 5 worker threads run in parallel (`DEEPAGENTS_WORKER_CONCURRENCY=5`).\n- Task results are retained for 7 days (`DEEPAGENTS_TASK_TTL_HOURS=168`).\n- Only the built-in read-only web-search and document-search tools are available.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,52,59,73,78,84,177,184,193,220,228,265,273,326,332,403,409,486,492,525],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","Deep Research",{"type":39,"tag":47,"props":48,"children":49},"p",{},[50],{"type":44,"value":51},"Delegate complex, long-running research and multi-document analysis to the DeepAgents background worker service.",{"type":39,"tag":53,"props":54,"children":56},"h2",{"id":55},"routing-rule",[57],{"type":44,"value":58},"Routing Rule",{"type":39,"tag":47,"props":60,"children":61},{},[62,64,71],{"type":44,"value":63},"For deep research, comprehensive analysis, or multi-step investigations, execute ",{"type":39,"tag":65,"props":66,"children":68},"code",{"className":67},[],[69],{"type":44,"value":70},"\u002Fsandbox\u002Fbin\u002Fdeep-research",{"type":44,"value":72},".",{"type":39,"tag":47,"props":74,"children":75},{},[76],{"type":44,"value":77},"Do not perform the same long-running task again inline after it has been delegated.",{"type":39,"tag":53,"props":79,"children":81},{"id":80},"how-to-use",[82],{"type":44,"value":83},"How To Use",{"type":39,"tag":85,"props":86,"children":91},"pre",{"className":87,"code":88,"language":89,"meta":90,"style":90},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","\u002Fsandbox\u002Fbin\u002Fdeep-research [--depth shallow|standard|deep] [--rubric \"\u003Ccustom criteria>\"] \"\u003Cresearch prompt or goal>\"\n","bash","",[92],{"type":39,"tag":65,"props":93,"children":94},{"__ignoreMap":90},[95],{"type":39,"tag":96,"props":97,"children":100},"span",{"class":98,"line":99},"line",1,[101,106,112,118,124,129,133,138,143,148,153,157,162,167,172],{"type":39,"tag":96,"props":102,"children":104},{"style":103},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[105],{"type":44,"value":70},{"type":39,"tag":96,"props":107,"children":109},{"style":108},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[110],{"type":44,"value":111}," [--depth ",{"type":39,"tag":96,"props":113,"children":115},{"style":114},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[116],{"type":44,"value":117},"shallow",{"type":39,"tag":96,"props":119,"children":121},{"style":120},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[122],{"type":44,"value":123},"|",{"type":39,"tag":96,"props":125,"children":126},{"style":103},[127],{"type":44,"value":128},"standard",{"type":39,"tag":96,"props":130,"children":131},{"style":120},[132],{"type":44,"value":123},{"type":39,"tag":96,"props":134,"children":135},{"style":103},[136],{"type":44,"value":137},"deep]",{"type":39,"tag":96,"props":139,"children":140},{"style":108},[141],{"type":44,"value":142}," [--rubric ",{"type":39,"tag":96,"props":144,"children":145},{"style":120},[146],{"type":44,"value":147},"\"",{"type":39,"tag":96,"props":149,"children":150},{"style":114},[151],{"type":44,"value":152},"\u003Ccustom criteria>",{"type":39,"tag":96,"props":154,"children":155},{"style":120},[156],{"type":44,"value":147},{"type":39,"tag":96,"props":158,"children":159},{"style":114},[160],{"type":44,"value":161},"]",{"type":39,"tag":96,"props":163,"children":164},{"style":120},[165],{"type":44,"value":166}," \"",{"type":39,"tag":96,"props":168,"children":169},{"style":114},[170],{"type":44,"value":171},"\u003Cresearch prompt or goal>",{"type":39,"tag":96,"props":173,"children":174},{"style":120},[175],{"type":44,"value":176},"\"\n",{"type":39,"tag":178,"props":179,"children":181},"h3",{"id":180},"examples",[182],{"type":44,"value":183},"Examples",{"type":39,"tag":47,"props":185,"children":186},{},[187],{"type":39,"tag":188,"props":189,"children":190},"strong",{},[191],{"type":44,"value":192},"Standard Research (Default):",{"type":39,"tag":85,"props":194,"children":196},{"className":87,"code":195,"language":89,"meta":90,"style":90},"\u002Fsandbox\u002Fbin\u002Fdeep-research \"Analysis of vector database performance benchmarks in 2026\"\n",[197],{"type":39,"tag":65,"props":198,"children":199},{"__ignoreMap":90},[200],{"type":39,"tag":96,"props":201,"children":202},{"class":98,"line":99},[203,207,211,216],{"type":39,"tag":96,"props":204,"children":205},{"style":103},[206],{"type":44,"value":70},{"type":39,"tag":96,"props":208,"children":209},{"style":120},[210],{"type":44,"value":166},{"type":39,"tag":96,"props":212,"children":213},{"style":114},[214],{"type":44,"value":215},"Analysis of vector database performance benchmarks in 2026",{"type":39,"tag":96,"props":217,"children":218},{"style":120},[219],{"type":44,"value":176},{"type":39,"tag":47,"props":221,"children":222},{},[223],{"type":39,"tag":188,"props":224,"children":225},{},[226],{"type":44,"value":227},"Deep Research:",{"type":39,"tag":85,"props":229,"children":231},{"className":87,"code":230,"language":89,"meta":90,"style":90},"\u002Fsandbox\u002Fbin\u002Fdeep-research --depth deep \"Research the 5 levels of agentic workflow platform security and draft a technical whitepaper\"\n",[232],{"type":39,"tag":65,"props":233,"children":234},{"__ignoreMap":90},[235],{"type":39,"tag":96,"props":236,"children":237},{"class":98,"line":99},[238,242,247,252,256,261],{"type":39,"tag":96,"props":239,"children":240},{"style":103},[241],{"type":44,"value":70},{"type":39,"tag":96,"props":243,"children":244},{"style":114},[245],{"type":44,"value":246}," --depth",{"type":39,"tag":96,"props":248,"children":249},{"style":114},[250],{"type":44,"value":251}," deep",{"type":39,"tag":96,"props":253,"children":254},{"style":120},[255],{"type":44,"value":166},{"type":39,"tag":96,"props":257,"children":258},{"style":114},[259],{"type":44,"value":260},"Research the 5 levels of agentic workflow platform security and draft a technical whitepaper",{"type":39,"tag":96,"props":262,"children":263},{"style":120},[264],{"type":44,"value":176},{"type":39,"tag":47,"props":266,"children":267},{},[268],{"type":39,"tag":188,"props":269,"children":270},{},[271],{"type":44,"value":272},"Custom Rubric Validation:",{"type":39,"tag":85,"props":274,"children":276},{"className":87,"code":275,"language":89,"meta":90,"style":90},"\u002Fsandbox\u002Fbin\u002Fdeep-research --depth deep --rubric \"Compare the alternatives in a table and cite each major factual claim\" \"Compare public retrieval architectures\"\n",[277],{"type":39,"tag":65,"props":278,"children":279},{"__ignoreMap":90},[280],{"type":39,"tag":96,"props":281,"children":282},{"class":98,"line":99},[283,287,291,295,300,304,309,313,317,322],{"type":39,"tag":96,"props":284,"children":285},{"style":103},[286],{"type":44,"value":70},{"type":39,"tag":96,"props":288,"children":289},{"style":114},[290],{"type":44,"value":246},{"type":39,"tag":96,"props":292,"children":293},{"style":114},[294],{"type":44,"value":251},{"type":39,"tag":96,"props":296,"children":297},{"style":114},[298],{"type":44,"value":299}," --rubric",{"type":39,"tag":96,"props":301,"children":302},{"style":120},[303],{"type":44,"value":166},{"type":39,"tag":96,"props":305,"children":306},{"style":114},[307],{"type":44,"value":308},"Compare the alternatives in a table and cite each major factual claim",{"type":39,"tag":96,"props":310,"children":311},{"style":120},[312],{"type":44,"value":147},{"type":39,"tag":96,"props":314,"children":315},{"style":120},[316],{"type":44,"value":166},{"type":39,"tag":96,"props":318,"children":319},{"style":114},[320],{"type":44,"value":321},"Compare public retrieval architectures",{"type":39,"tag":96,"props":323,"children":324},{"style":120},[325],{"type":44,"value":176},{"type":39,"tag":53,"props":327,"children":329},{"id":328},"options-arguments",[330],{"type":44,"value":331},"Options & Arguments",{"type":39,"tag":333,"props":334,"children":335},"ul",{},[336,348,358,368,379,398],{"type":39,"tag":337,"props":338,"children":339},"li",{},[340,346],{"type":39,"tag":65,"props":341,"children":343},{"className":342},[],[344],{"type":44,"value":345},"--depth \u003Cshallow|standard|deep>",{"type":44,"value":347},": Execution depth preset:",{"type":39,"tag":337,"props":349,"children":350},{},[351,356],{"type":39,"tag":65,"props":352,"children":354},{"className":353},[],[355],{"type":44,"value":117},{"type":44,"value":357},": 25 graph steps, 1 rubric iteration",{"type":39,"tag":337,"props":359,"children":360},{},[361,366],{"type":39,"tag":65,"props":362,"children":364},{"className":363},[],[365],{"type":44,"value":128},{"type":44,"value":367}," (default): 50 graph steps, 2 rubric iterations",{"type":39,"tag":337,"props":369,"children":370},{},[371,377],{"type":39,"tag":65,"props":372,"children":374},{"className":373},[],[375],{"type":44,"value":376},"deep",{"type":44,"value":378},": 100 graph steps, 3 rubric iterations",{"type":39,"tag":337,"props":380,"children":381},{},[382,388,390,396],{"type":39,"tag":65,"props":383,"children":385},{"className":384},[],[386],{"type":44,"value":387},"--rubric \"\u003Ctext>\"",{"type":44,"value":389},": Optional custom quality rubric for ",{"type":39,"tag":65,"props":391,"children":393},{"className":392},[],[394],{"type":44,"value":395},"RubricMiddleware",{"type":44,"value":397}," cross-validation. If omitted, the worker creates a request-specific evidence rubric before invocation.",{"type":39,"tag":337,"props":399,"children":400},{},[401],{"type":44,"value":402},"Position 1: The research prompt or goal (required string)",{"type":39,"tag":53,"props":404,"children":406},{"id":405},"how-it-works",[407],{"type":44,"value":408},"How It Works",{"type":39,"tag":410,"props":411,"children":412},"ol",{},[413,423,441,459,476],{"type":39,"tag":337,"props":414,"children":415},{},[416,421],{"type":39,"tag":188,"props":417,"children":418},{},[419],{"type":44,"value":420},"Task Enqueued",{"type":44,"value":422},": Submitted to the DeepAgents worker service via SQLite queue.",{"type":39,"tag":337,"props":424,"children":425},{},[426,431,433,439],{"type":39,"tag":188,"props":427,"children":428},{},[429],{"type":44,"value":430},"Planning",{"type":44,"value":432},": The worker initializes ",{"type":39,"tag":65,"props":434,"children":436},{"className":435},[],[437],{"type":44,"value":438},"write_todos",{"type":44,"value":440}," and applies either the supplied rubric or a request-specific default rubric.",{"type":39,"tag":337,"props":442,"children":443},{},[444,449,451,457],{"type":39,"tag":188,"props":445,"children":446},{},[447],{"type":44,"value":448},"SubAgent Delegation",{"type":44,"value":450},": Research subtopics are delegated to isolated ",{"type":39,"tag":65,"props":452,"children":454},{"className":453},[],[455],{"type":44,"value":456},"SubAgent",{"type":44,"value":458}," workers to prevent context window saturation.",{"type":39,"tag":337,"props":460,"children":461},{},[462,467,469,474],{"type":39,"tag":188,"props":463,"children":464},{},[465],{"type":44,"value":466},"Cross-Validation",{"type":44,"value":468},": ",{"type":39,"tag":65,"props":470,"children":472},{"className":471},[],[473],{"type":44,"value":395},{"type":44,"value":475}," evaluates the output against the quality rubric, triggering iterative refinement loops if criteria are not met.",{"type":39,"tag":337,"props":477,"children":478},{},[479,484],{"type":39,"tag":188,"props":480,"children":481},{},[482],{"type":44,"value":483},"Output Delivered",{"type":44,"value":485},": Formatted report is returned to stdout.",{"type":39,"tag":53,"props":487,"children":489},{"id":488},"execution-constraints",[490],{"type":44,"value":491},"Execution Constraints",{"type":39,"tag":333,"props":493,"children":494},{},[495,508,520],{"type":39,"tag":337,"props":496,"children":497},{},[498,500,506],{"type":44,"value":499},"Up to 5 worker threads run in parallel (",{"type":39,"tag":65,"props":501,"children":503},{"className":502},[],[504],{"type":44,"value":505},"DEEPAGENTS_WORKER_CONCURRENCY=5",{"type":44,"value":507},").",{"type":39,"tag":337,"props":509,"children":510},{},[511,513,519],{"type":44,"value":512},"Task results are retained for 7 days (",{"type":39,"tag":65,"props":514,"children":516},{"className":515},[],[517],{"type":44,"value":518},"DEEPAGENTS_TASK_TTL_HOURS=168",{"type":44,"value":507},{"type":39,"tag":337,"props":521,"children":522},{},[523],{"type":44,"value":524},"Only the built-in read-only web-search and document-search tools are available.",{"type":39,"tag":526,"props":527,"children":528},"style",{},[529],{"type":44,"value":530},"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":532,"total":634},[533,549,564,583,589,601,617],{"slug":534,"name":534,"fn":535,"description":536,"org":537,"tags":538,"stars":22,"repoUrl":23,"updatedAt":548},"axe-a11y","audit web accessibility with axe-core","Automated web accessibility scanning (axe-core) driven by patchright + real Google Chrome — audits sites behind bot walls and behind auth",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[539,542,545],{"name":540,"slug":541,"type":15},"Accessibility","accessibility",{"name":543,"slug":544,"type":15},"QA","qa",{"name":546,"slug":547,"type":15},"Testing","testing","2026-08-31T09:19:20.559156",{"slug":550,"name":550,"fn":551,"description":552,"org":553,"tags":554,"stars":22,"repoUrl":23,"updatedAt":563},"blackwall-payment-gate","screen and submit x402 payments","Screen x402 payments with an advisory Blackwall verdict, then submit a payment intent to the host-side release gate. You prepare payments; only the gate can settle them.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[555,558,561],{"name":556,"slug":557,"type":15},"Payments","payments",{"name":559,"slug":560,"type":15},"Security","security",{"name":562,"slug":562,"type":15},"x402","2026-08-31T09:19:25.64269",{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":22,"repoUrl":23,"updatedAt":582},"cross-source-gap-analysis","identify alignment gaps across communication sources","Compare findings across Slack, GitHub, NVIDIA forums, and Outlook to identify alignment gaps, missing coverage, and follow-ups.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[570,573,576,579],{"name":571,"slug":572,"type":15},"Analysis","analysis",{"name":574,"slug":575,"type":15},"GitHub","github",{"name":577,"slug":578,"type":15},"Outlook Email","outlook-email",{"name":580,"slug":581,"type":15},"Slack","slack","2026-08-21T03:36:36.438375",{"slug":4,"name":4,"fn":5,"description":6,"org":584,"tags":585,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[586,587,588],{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"slug":590,"name":590,"fn":591,"description":592,"org":593,"tags":594,"stars":22,"repoUrl":23,"updatedAt":600},"github-readonly-live","read live GitHub repository data","Read an allowed live GitHub repository through authenticated, policy-scoped GitHub REST GET requests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[595,598,599],{"name":596,"slug":597,"type":15},"API Development","api-development",{"name":574,"slug":575,"type":15},{"name":9,"slug":8,"type":15},"2026-08-21T03:36:35.451173",{"slug":602,"name":602,"fn":603,"description":604,"org":605,"tags":606,"stars":22,"repoUrl":23,"updatedAt":616},"gitlab-readonly-live","read GitLab project data","Read one of the configured GitLab projects through authenticated, policy-scoped REST GET requests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[607,610,613],{"name":608,"slug":609,"type":15},"Git","git",{"name":611,"slug":612,"type":15},"GitLab","gitlab",{"name":614,"slug":615,"type":15},"REST API","rest-api","2026-08-31T09:19:36.855848",{"slug":618,"name":618,"fn":619,"description":620,"org":621,"tags":622,"stars":22,"repoUrl":23,"updatedAt":633},"inbound-judging","triage incoming email and Slack messages","Decide which newly-arrived email and Slack messages create an obligation for the user, and craft the row that represents each one.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[623,626,629,630],{"name":624,"slug":625,"type":15},"Email","email",{"name":627,"slug":628,"type":15},"Messaging","messaging",{"name":580,"slug":581,"type":15},{"name":631,"slug":632,"type":15},"Triage","triage","2026-08-31T09:19:11.560469",28,{"items":636,"total":787},[637,655,673,684,694,706,719,733,742,753,767,776],{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":652,"repoUrl":653,"updatedAt":654},"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},[643,646,649],{"name":644,"slug":645,"type":15},"Documentation","documentation",{"name":647,"slug":648,"type":15},"MCP","mcp",{"name":650,"slug":651,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-08-25T03:29:57.273192",{"slug":656,"name":656,"fn":657,"description":658,"org":659,"tags":660,"stars":670,"repoUrl":671,"updatedAt":672},"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},[661,664,667],{"name":662,"slug":663,"type":15},"Containers","containers",{"name":665,"slug":666,"type":15},"Deployment","deployment",{"name":668,"slug":669,"type":15},"Python","python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":674,"name":674,"fn":675,"description":676,"org":677,"tags":678,"stars":670,"repoUrl":671,"updatedAt":683},"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},[679,682],{"name":680,"slug":681,"type":15},"CI\u002FCD","ci-cd",{"name":665,"slug":666,"type":15},"2026-07-14T05:25:59.97109",{"slug":685,"name":685,"fn":686,"description":687,"org":688,"tags":689,"stars":670,"repoUrl":671,"updatedAt":693},"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},[690,691,692],{"name":680,"slug":681,"type":15},{"name":665,"slug":666,"type":15},{"name":574,"slug":575,"type":15},"2026-08-28T14:38:16.959248",{"slug":695,"name":695,"fn":696,"description":697,"org":698,"tags":699,"stars":670,"repoUrl":671,"updatedAt":705},"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},[700,703,704],{"name":701,"slug":702,"type":15},"Debugging","debugging",{"name":574,"slug":575,"type":15},{"name":631,"slug":632,"type":15},"2026-07-14T05:25:57.442089",{"slug":707,"name":707,"fn":708,"description":709,"org":710,"tags":711,"stars":670,"repoUrl":671,"updatedAt":718},"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},[712,715],{"name":713,"slug":714,"type":15},"Best Practices","best-practices",{"name":716,"slug":717,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":720,"name":720,"fn":721,"description":722,"org":723,"tags":724,"stars":670,"repoUrl":671,"updatedAt":732},"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, including the mechanical steps for transferring an existing pretrain_gpt.py launch script.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[725,728,731],{"name":726,"slug":727,"type":15},"Machine Learning","machine-learning",{"name":729,"slug":730,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-08-21T03:36:57.470256",{"slug":734,"name":734,"fn":735,"description":736,"org":737,"tags":738,"stars":670,"repoUrl":671,"updatedAt":741},"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},[739,740],{"name":543,"slug":544,"type":15},{"name":546,"slug":547,"type":15},"2026-07-14T05:25:53.673039",{"slug":743,"name":743,"fn":744,"description":745,"org":746,"tags":747,"stars":670,"repoUrl":671,"updatedAt":752},"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},[748,749],{"name":665,"slug":666,"type":15},{"name":750,"slug":751,"type":15},"Infrastructure","infrastructure","2026-07-14T05:25:49.362534",{"slug":754,"name":754,"fn":755,"description":756,"org":757,"tags":758,"stars":670,"repoUrl":671,"updatedAt":766},"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},[759,762,763],{"name":760,"slug":761,"type":15},"Code Review","code-review",{"name":574,"slug":575,"type":15},{"name":764,"slug":765,"type":15},"Pull Requests","pull-requests","2026-08-25T03:29:16.211287",{"slug":768,"name":768,"fn":769,"description":770,"org":771,"tags":772,"stars":670,"repoUrl":671,"updatedAt":775},"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},[773,774],{"name":543,"slug":544,"type":15},{"name":546,"slug":547,"type":15},"2026-07-14T05:25:54.928983",{"slug":777,"name":777,"fn":778,"description":779,"org":780,"tags":781,"stars":670,"repoUrl":671,"updatedAt":786},"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},[782,785],{"name":783,"slug":784,"type":15},"Automation","automation",{"name":680,"slug":681,"type":15},"2026-07-30T05:29:03.275638",563]