[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DFYV2KPZR9RE0Q3KV07F68":3,"skill-same:01M6DFYV2KPZR9RE0Q3KV07F68":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":6,"ownerHtmlUrl":68,"ownerBlogUrl":6,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6DFYV2KPZR9RE0Q3KV07F68","hermes-a2a-multi-agent",null,"Set up Hermes A2A inter-agent communication.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F54\u002F54fec62692dcd3e8e20e3d239aa93c1e0af791374429bcbedeb7083b99c34603\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"hermes","hermes a2a multi agent","multi agent","a2a","hermes agent","linux","peer","AI-agents","agent communication","up","ops","autonomous","heartbeat","memory","peer-to-peer","SET","communication","create","windows","orchestration","2026-11-10 10:12:30",false,"---\r\nname: hermes-a2a-multi-agent\r\ndescription: Set up Hermes A2A inter-agent communication.\r\nversion: 1.0.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [a2a, multi-agent, peer-to-peer, orchestration, profiles]\r\n    category: autonomous-ai-agents\r\n    related_skills: [hermes-agent, agent-heartbeat-and-memory-ops, create-company-ai-employees]\r\n---\r\n\r\n# Hermes A2A Multi-Agent Communication\r\n\r\nHermes ships built-in A2A (Agent-to-Agent) tools for peer-to-peer inter-agent messaging and multi-agent orchestration. This is NOT a separate daemon or script — it's a toolset enabled in config.yaml and invoked directly by the agent.\r\n\r\n## When to Use\r\n\r\n- The user wants multiple Hermes profiles (or remote instances) to talk to each other\r\n- Setting up Bot Mode with inter-agent messaging\r\n- Delegating tasks between agents with different capabilities\r\n- Coordinating multi-step workflows across agents (researcher → writer → reviewer)\r\n- Troubleshooting A2A peer discovery, registration, or messaging failures\r\n\r\n## Available Tools\r\n\r\n| Tool | Purpose | Key Params |\r\n|------|---------|------------|\r\n| `a2a_list` | List registered peers + metrics | — |\r\n| `a2a_discover` | Find a peer by URL | `url` (required) |\r\n| `a2a_call` | Send message to a peer | peer, message |\r\n| `a2a_orchestrate` | Coordinate multi-agent workflow | plan, agents |\r\n| `a2a_history` | View message history with a peer | peer |\r\n\r\n**IMPORTANT**: `a2a_call` and `a2a_orchestrate` are **NOT deferrable tools** — `tool_describe` will fail on them with \"not a deferrable tool.\" This is normal. Call them directly.\r\n\r\n## Setup: Enabling A2A (Correct Config Structure)\r\n\r\nThe A2A platform is enabled under `platforms.a2a` in config.yaml (NOT `gateway.platforms.a2a`).\r\n\r\n```yaml\r\nplatforms:\r\n  a2a:\r\n    enabled: true\r\n    extra:\r\n      port: 9900\r\n      host: 127.0.0.1\r\n```\r\n\r\nAlso ensure `a2a` is in `platform_toolsets.cli`:\r\n\r\n```yaml\r\nplatform_toolsets:\r\n  cli:\r\n    - a2a\r\n```\r\n\r\nRestart the gateway: `Ctrl+K → Restart gateway` (or `\u002Frestart`).\r\n\r\n## Setup: Adding Peers\r\n\r\nPeers are registered under `a2a_agents` in config.yaml:\r\n\r\n```yaml\r\na2a_agents:\r\n  job-seeker:\r\n    url: http:\u002F\u002F127.0.0.1:9901\r\n    timeout: 120\r\n  secretary:\r\n    url: http:\u002F\u002F127.0.0.1:9902\r\n    timeout: 120\r\n```\r\n\r\n**NOTE**: The `hermes config set` command warns \"not a recognized config key\" for `a2a_agents.*`. This is a false warning — use `--force` to suppress it. The A2A plugin reads these keys at runtime.\r\n\r\n## Verifying A2A is Running\r\n\r\nAfter gateway restart, check the Agent Card endpoint:\r\n\r\n```bash\r\ncurl -sS http:\u002F\u002F127.0.0.1:9900\u002F.well-known\u002Fagent-card.json\r\n```\r\n\r\nA valid JSON response with `\"name\"`, `\"url\"`, and `\"supportedInterfaces\"` confirms A2A is active.\r\n\r\n## Critical Limitation: Single Gateway Instance\r\n\r\n`hermes gateway run` uses a PID file (`~\u002F.hermes\u002Fgateway.pid`) to enforce a single running instance per profile. Attempting to start a second profile's gateway fails with:\r\n\r\n```\r\n✗ Another gateway instance is already running (PID XXXXX).\r\n```\r\n\r\nThis means you **cannot** run multiple A2A servers (one per profile) simultaneously on the same machine via the normal gateway.\r\n\r\n## Recommended Same-Machine Pattern: Hub + Spoke\r\n\r\nFor multi-profile inter-agent communication on one machine, use a **hub-spoke** architecture:\r\n\r\n```\r\n[default :9900] ← A2A server (always-on hub)\r\n    │\r\n    ├─ terminal → hermes -p job-seeker chat -q '\u003Ctask>'\r\n    └─ terminal → hermes -p secretary chat -q '\u003Ctask>'\r\n```\r\n\r\n- **default** runs the A2A server and acts as the coordinator\r\n- **Other profiles** are invoked one-shot via `hermes -p \u003Cprofile> chat -q '\u003Ctask>'` from the hub's terminal tool\r\n- Results return to the hub, which can relay them via A2A or act on them\r\n\r\n### One-Shot Call Pattern\r\n\r\n```bash\r\n# From hub terminal, call a spoke profile:\r\nhermes -p job-seeker --provider nous -m meituan\u002Flongcat-2.0:free chat -q '求人検索して'\r\nhermes -p secretary --provider nous -m meituan\u002Flongcat-2.0:free chat -q 'スケジュール確認'\r\n```\r\n\r\n**NOTE**: The `-m` flag alone may not route to the correct provider. Always pair with `--provider` flag when calling profiles whose default provider differs from the hub's.\r\n\r\n## Common Patterns\r\n\r\n### Bot Mode + A2A\r\nThe desktop Bot Mode plugin (`hermes-bots`) shows one row per profile in the left pane. Bots can A2A-message each other into their canonical \\\"Bot Chat\\\" — useful for multi-agent task delegation with a visual roster.\r\n\r\n### Task Delegation\r\nUse `a2a_call` to assign a task to a peer with the right capabilities (e.g., a profile with `code_execution` enabled sends compute work to a profile with more RAM).\r\n\r\n### Orchestration\r\nUse `a2a_orchestrate` for multi-step workflows that span agents — e.g., researcher gathers sources, writer drafts, reviewer critiques.\r\n\r\n## Troubleshooting\r\n\r\n| Symptom | Cause | Fix |\r\n|---------|-------|-----|\r\n| `a2a_list` → \"No peers configured\" | No `a2a_agents` in config | Add peer entries to config.yaml |\r\n| `a2a_discover` → \"'url' is required\" | Missing URL param | Pass the peer's A2A endpoint URL |\r\n| `tool_describe` fails on `a2a_call` | Not a deferrable tool | Call directly; don't use tool_describe |\r\n| Tools not appearing in session | `a2a` not in platform_toolsets | Add to `platform_toolsets.cli`, restart gateway |\r\n\r\n## References\r\n\r\n- `references\u002Fa2a-tool-usage.md` — detailed parameter shapes, anti-loop behavior, metrics interpretation, and config paths.\r\n- `references\u002Fhub-spoke-architecture.md` — verified same-machine multi-profile pattern (hub A2A server + spoke `chat -q` invocations).\r\n- `templates\u002Fa2a-config-template.yaml` — copy-paste config blocks for quick setup.","# Hermes A2A Multi-Agent Communication\r\n\r\nHermes ships built-in A2A (Agent-to-Agent) tools for peer-to-peer inter-agent messaging and multi-agent orchestration. This is NOT a separate daemon or script — it's a toolset enabled in config.yaml and invoked directly by the agent.\r\n\r\n## When to Use\r\n\r\n- The user wants multiple Hermes profiles (or remote instances) to talk to each other\r\n- Setting up Bot Mode with inter-agent messaging\r\n- Delegating tasks between agents with different capabilities\r\n- Coordinating multi-step workflows across agents (researcher → writer → reviewer)\r\n- Troubleshooting A2A peer discovery, registration, or messaging failures\r\n\r\n## Available Tools\r\n\r\n| Tool | Purpose | Key Params |\r\n|------|---------|------------|\r\n| `a2a_list` | List registered peers + metrics | — |\r\n| `a2a_discover` | Find a peer by URL | `url` (required) |\r\n| `a2a_call` | Send message to a peer | peer, message |\r\n| `a2a_orchestrate` | Coordinate multi-agent workflow | plan, agents |\r\n| `a2a_history` | View message history with a peer | peer |\r\n\r\n**IMPORTANT**: `a2a_call` and `a2a_orchestrate` are **NOT deferrable tools** — `tool_describe` will fail on them with \"not a deferrable tool.\" This is normal. Call them directly.\r\n\r\n## Setup: Enabling A2A (Correct Config Structure)\r\n\r\nThe A2A platform is enabled under `platforms.a2a` in config.yaml (NOT `gateway.platforms.a2a`).\r\n\r\n```yaml\r\nplatforms:\r\n  a2a:\r\n    enabled: true\r\n    extra:\r\n      port: 9900\r\n      host: 127.0.0.1\r\n```\r\n\r\nAlso ensure `a2a` is in `platform_toolsets.cli`:\r\n\r\n```yaml\r\nplatform_toolsets:\r\n  cli:\r\n    - a2a\r\n```\r\n\r\nRestart the gateway: `Ctrl+K → Restart gateway` (or `\u002Frestart`).\r\n\r\n## Setup: Adding Peers\r\n\r\nPeers are registered under `a2a_agents` in config.yaml:\r\n\r\n```yaml\r\na2a_agents:\r\n  job-seeker:\r\n    url: http:\u002F\u002F127.0.0.1:9901\r\n    timeout: 120\r\n  secretary:\r\n    url: http:\u002F\u002F127.0.0.1:9902\r\n    timeout: 120\r\n```\r\n\r\n**NOTE**: The `hermes config set` command warns \"not a recognized config key\" for `a2a_agents.*`. This is a false warning — use `--force` to suppress it. The A2A plugin reads these keys at runtime.\r\n\r\n## Verifying A2A is Running\r\n\r\nAfter gateway restart, check the Agent Card endpoint:\r\n\r\n```bash\r\ncurl -sS http:\u002F\u002F127.0.0.1:9900\u002F.well-known\u002Fagent-card.json\r\n```\r\n\r\nA valid JSON response with `\"name\"`, `\"url\"`, and `\"supportedInterfaces\"` confirms A2A is active.\r\n\r\n## Critical Limitation: Single Gateway Instance\r\n\r\n`hermes gateway run` uses a PID file (`~\u002F.hermes\u002Fgateway.pid`) to enforce a single running instance per profile. Attempting to start a second profile's gateway fails with:\r\n\r\n```\r\n✗ Another gateway instance is already running (PID XXXXX).\r\n```\r\n\r\nThis means you **cannot** run multiple A2A servers (one per profile) simultaneously on the same machine via the normal gateway.\r\n\r\n## Recommended Same-Machine Pattern: Hub + Spoke\r\n\r\nFor multi-profile inter-agent communication on one machine, use a **hub-spoke** architecture:\r\n\r\n```\r\n[default :9900] ← A2A server (always-on hub)\r\n    │\r\n    ├─ terminal → hermes -p job-seeker chat -q '\u003Ctask>'\r\n    └─ terminal → hermes -p secretary chat -q '\u003Ctask>'\r\n```\r\n\r\n- **default** runs the A2A server and acts as the coordinator\r\n- **Other profiles** are invoked one-shot via `hermes -p \u003Cprofile> chat -q '\u003Ctask>'` from the hub's terminal tool\r\n- Results return to the hub, which can relay them via A2A or act on them\r\n\r\n### One-Shot Call Pattern\r\n\r\n```bash\r\n# From hub terminal, call a spoke profile:\r\nhermes -p job-seeker --provider nous -m meituan\u002Flongcat-2.0:free chat -q '求人検索して'\r\nhermes -p secretary --provider nous -m meituan\u002Flongcat-2.0:free chat -q 'スケジュール確認'\r\n```\r\n\r\n**NOTE**: The `-m` flag alone may not route to the correct provider. Always pair with `--provider` flag when calling profiles whose default provider differs from the hub's.\r\n\r\n## Common Patterns\r\n\r\n### Bot Mode + A2A\r\nThe desktop Bot Mode plugin (`hermes-bots`) shows one row per profile in the left pane. Bots can A2A-message each other into their canonical \\\"Bot Chat\\\" — useful for multi-agent task delegation with a visual roster.\r\n\r\n### Task Delegation\r\nUse `a2a_call` to assign a task to a peer with the right capabilities (e.g., a profile with `code_execution` enabled sends compute work to a profile with more RAM).\r\n\r\n### Orchestration\r\nUse `a2a_orchestrate` for multi-step workflows that span agents — e.g., researcher gathers sources, writer drafts, reviewer critiques.\r\n\r\n## Troubleshooting\r\n\r\n| Symptom | Cause | Fix |\r\n|---------|-------|-----|\r\n| `a2a_list` → \"No peers configured\" | No `a2a_agents` in config | Add peer entries to config.yaml |\r\n| `a2a_discover` → \"'url' is required\" | Missing URL param | Pass the peer's A2A endpoint URL |\r\n| `tool_describe` fails on `a2a_call` | Not a deferrable tool | Call directly; don't use tool_describe |\r\n| Tools not appearing in session | `a2a` not in platform_toolsets | Add to `platform_toolsets.cli`, restart gateway |\r\n\r\n## References\r\n\r\n- `references\u002Fa2a-tool-usage.md` — detailed parameter shapes, anti-loop behavior, metrics interpretation, and config paths.\r\n- `references\u002Fhub-spoke-architecture.md` — verified same-machine multi-profile pattern (hub A2A server + spoke `chat -q` invocations).\r\n- `templates\u002Fa2a-config-template.yaml` — copy-paste config blocks for quick setup.",{"name":5,"author":49,"license":15,"version":50,"metadata":51,"platforms":61,"description":7},"Hermes Agent","1.0.0",{"hermes":52},{"tags":53,"category":56,"related_skills":57},[27,54,38,43,55],"multi-agent","profiles","autonomous-ai-agents",[58,59,60],"hermes-agent","agent-heartbeat-and-memory-ops","create-company-ai-employees",[29,62,42],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F54\u002F54fec62692dcd3e8e20e3d239aa93c1e0af791374429bcbedeb7083b99c34603",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add zapabob\u002FSkills --skill hermes-a2a-multi-agent",{"tool":77,"command":78},"bunx","bunx skills add zapabob\u002FSkills --skill hermes-a2a-multi-agent",{"tool":80,"command":81},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill hermes-a2a-multi-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F54\u002F54fec62692dcd3e8e20e3d239aa93c1e0af791374429bcbedeb7083b99c34603\u002FSKILL.md",true,[],[86,115,150,177,204,221],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":101,"publishedAt":44},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[92,95,96],{"categoryNo":93,"categoryName":94,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[88,102,62,103,104,29,42,105,106,107,108,109,110,24,28,111,63,112,113,114],"openclaw","cli","github","official","search","https","social-media","api","Media","twitter","social","via","post",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":132,"publishedAt":44},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[121,124,127,128,129],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":130,"categoryName":131,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者",[133,134,135,136,62,137,29,138,42,139,140,141,142,143,144,145,146,147,148,149],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":159,"publishedAt":44},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[156],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[152,62,29,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":44},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[187,62,188,189,42,190,191,192,193,194,195,167,196,197,198,199,200,201,202,203],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":211,"publishedAt":44},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[210],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[206,62,212,104,29,213,214,215,216,217,218,24,28,219,220],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":229,"publishedAt":44},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[227,228],{"categoryNo":93,"categoryName":94,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[230,231,232,29,233,160,234,235,236,163,237,109,238,239,240,241,242,243,244,245],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]