{"id":"6cd2ea93-b335-4907-aa4f-45f4c4b455e6","entityType":"agent","slug":"crewai-764137119-hello-agent","name":"hello_agent","canonicalUrl":"https://www.xpersona.co/agent/crewai-764137119-hello-agent","canonicalPath":"/agent/crewai-764137119-hello-agent","generatedAt":"2026-10-10T03:52:43.071Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T18:18:12.050Z","emptyReason":null},"description":"crewai 框架应用 该项目的环境目录如下 ~/work/golang/crewai-agent 命令 source .venv/bin/activate 在此目录下执行 crewai 如何做到 像vscode 插件中的 plan. act 模式。 先plan. 人工确认后切到act 这个需求用 CrewAI 的 **Flow + @human_feedback + @router** 组合就可以实现。我给你设计一个完整的 Plan → Act 模式： 架构设计 完整代码示例 项目结构 1. Plan Crew（生成计划） **crews/plan_crew/config/agents.yaml**： **crews/plan_crew/config/tasks.yaml**： 2. Act Crew（执行计划） **crews/act_crew/config/agents.yaml**： **crews/act_crew/config/tasks.","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/764137119/hello_agent","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/764137119/hello_agent","kind":"source"}],"safetyScore":66,"overallRank":18.6,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"crewai 框架应用 该项目的环境目录如下 ~/work/golang/crewai-agent 命令 source .venv/bin/activate 在此目录下执行 crewai 如何做到 像vscode 插件中的 plan. act 模式。 先plan. 人工确认后切到act 这个需求用 CrewAI 的 *"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:18:12.050Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T18:18:12.050Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:18:12.046Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T18:18:12.050Z","lastCrawledAt":"2026-10-09T18:18:12.046Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T18:18:12.046Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T03:52:43.071Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-764137119-hello-agent/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T18:18:12.050Z","emptyReason":null},"readme":"```bash\n### 方式一：用 crewai CLI（推荐）\n### 构建虚拟环境\nuv venv 是 Python 包管理工具 uv 提供的命令，用于创建 Python 虚拟环境。\nuv venv {{虚拟环境名称}}\nuv venv {{虚拟环境名称}} --python 3.12 ##指定python 版本\n ### 启动虚拟环境\nsource .venv/bin/activate\n### 虚拟环境内执行\nuv pip install crewai \n### 创建项目\ncrewai create crew hello-agent\n\n\n\n# 先在项目根目录安装依赖\nuv sync\n\n# 然后运行\nuv run\n\n## 退出虚拟环境\n\ndeactivate\n```\n\n该项目的环境目录如下 \n~/work/golang/crewai-agent\n命令 source .venv/bin/activate 在此目录下执行\n\n\n### crewai 如何做到 像vscode 插件中的 plan. act 模式。 先plan. 人工确认后切到act\n\n这个需求用 CrewAI 的 **Flow + `@human_feedback` + `@router`** 组合就可以实现。我给你设计一个完整的 Plan → Act 模式：\n\n## 架构设计\n\n```\n         @start()\n            │\n            ▼\n    ┌─────────────────┐\n    │  Plan Crew       │  ← AI 先生成计划\n    │  (planner agent) │\n    └────────┬────────┘\n             │ 输出计划\n             ▼\n    ┌─────────────────┐\n    │  @human_feedback │  ← 展示计划给人类，等待确认\n    │   \"请审核该计划\"  │\n    └────────┬────────┘\n             │\n      ┌──────┴──────┐\n      ▼              ▼\n  \"approved\"     \"rejected\"\n      │              │\n      ▼              ▼\n┌──────────┐  ┌──────────┐\n│ Act Crew  │  │ 返回修改  │\n│ 执行计划  │  │ 重新规划  │\n└──────────┘  └──────────┘\n```\n\n## 完整代码示例\n\n### 项目结构\n```\nsrc/my_flow/\n├── crews/\n│   ├── plan_crew/            # Plan Crew\n│   │   ├── config/\n│   │   │   ├── agents.yaml\n│   │   │   └── tasks.yaml\n│   │   └── plan_crew.py\n│   └── act_crew/             # Act Crew\n│       ├── config/\n│       │   ├── agents.yaml\n│       │   └── tasks.yaml\n│       └── act_crew.py\n├── main.py                   # Flow 编排\n└── flow.py                   # Plan → Act 流程\n```\n\n### 1. Plan Crew（生成计划）\n\n**`crews/plan_crew/config/agents.yaml`**：\n```yaml\nplanner:\n  role: >\n    {topic} Strategy Planner\n  goal: >\n    Create a detailed step-by-step plan for {topic}\n  backstory: >\n    You're a strategic planner who breaks down complex topics\n    into actionable steps. Known for your clear and structured plans.\n```\n\n**`crews/plan_crew/config/tasks.yaml`**：\n```yaml\nplanning_task:\n  description: >\n    Create a detailed plan for: {topic}\n    Break it down into clear, actionable steps.\n    Consider timeline, resources needed, and potential risks.\n  expected_output: >\n    A detailed plan with 5-10 steps, each step including:\n    - What needs to be done\n    - Expected outcome\n    - Dependencies (if any)\n    Format as markdown.\n  agent: planner\n```\n\n### 2. Act Crew（执行计划）\n\n**`crews/act_crew/config/agents.yaml`**：\n```yaml\nexecutor:\n  role: >\n    {topic} Execution Specialist\n  goal: >\n    Execute the approved plan for {topic} step by step\n  backstory: >\n    You're a reliable executor who follows plans precisely.\n    You complete each step thoroughly before moving to the next.\n```\n\n**`crews/act_crew/config/tasks.yaml`**：\n```yaml\nexecution_task:\n  description: >\n    Execute the following plan step by step:\n    \n    {plan}\n    \n    Complete each step thoroughly. Report progress after each step.\n  expected_output: >\n    A complete execution report with:\n    - Each step executed\n    - Results achieved\n    - Any challenges encountered and how they were resolved\n  agent: executor\n```\n\n### 3. Flow 编排（核心）\n\n**`flow.py`**：\n```python\nfrom crewai.flow.flow import Flow, listen, router, start\nfrom crewai.flow.human_feedback import human_feedback\nfrom pydantic import BaseModel\n\nfrom my_flow.crews.plan_crew.plan_crew import PlanCrew\nfrom my_flow.crews.act_crew.act_crew import ActCrew\n\nclass PlanActState(BaseModel):\n    topic: str = \"\"\n    plan: str = \"\"\n    result: str = \"\"\n\nclass PlanActFlow(Flow[PlanActState]):\n\n    @start()\n    def generate_plan(self):\n        \"\"\"Step 1: AI 先生成计划\"\"\"\n        print(\"\\n🤖 AI is generating a plan...\\n\")\n        \n        result = PlanCrew().crew().kickoff(\n            inputs={\"topic\": self.state.topic}\n        )\n        self.state.plan = result.raw\n        \n        print(\"\\n\" + \"=\"*50)\n        print(\"📋 AI 生成的计划:\")\n        print(\"=\"*50)\n        print(self.state.plan)\n        print(\"=\"*50)\n        \n        return self.state.plan\n\n    @router(generate_plan)\n    @human_feedback(\n        message=\"请审核上面的计划，是否同意执行？\",\n        emit=[\"approved\", \"rejected\"],\n    )\n    def review_plan(self, plan: str):\n        \"\"\"Step 2: 等待人工审核\"\"\"\n        # human_feedback 会暂停，等待用户在终端输入\n        # 根据输入内容自动路由到 \"approved\" 或 \"rejected\"\n        return plan\n\n    @listen(\"approved\")\n    def execute_plan(self, plan: str):\n        \"\"\"Step 3: 人工同意后执行\"\"\"\n        print(\"\\n✅ Plan approved! Executing...\\n\")\n        \n        result = ActCrew().crew().kickoff(\n            inputs={\n                \"topic\": self.state.topic,\n                \"plan\": self.state.plan,\n            }\n        )\n        self.state.result = result.raw\n        \n        print(\"\\n\" + \"=\"*50)\n        print(\"📊 执行结果:\")\n        print(\"=\"*50)\n        print(self.state.result)\n        \n        return self.state.result\n\n    @listen(\"rejected\")\n    def revise_plan(self):\n        \"\"\"Step 4: 被拒绝后重新生成\"\"\"\n        print(\"\\n❌ Plan rejected. Let me revise...\\n\")\n        \n        # 可以在这里获取人类反馈\n        feedback = self.last_human_feedback\n        print(f\"📝 Human feedback: {feedback}\")\n        \n        # 重新规划（回到第一步，或者用反馈优化）\n        return self.generate_plan()\n```\n\n**`main.py`**：\n```python\n#!/usr/bin/env python\nfrom my_flow.flow import PlanActFlow\n\ndef kickoff():\n    flow = PlanActFlow()\n    result = flow.kickoff(inputs={\"topic\": \"AI Agent 开发最佳实践\"})\n    print(f\"\\n最终结果: {result}\")\n\nif __name__ == \"__main__\":\n    kickoff()\n```\n\n## 运行效果\n\n```\n🤖 AI is generating a plan...\n\n==================================================\n📋 AI 生成的计划:\n==================================================\nStep 1: 研究现有的 AI Agent 框架...\nStep 2: 比较不同框架的优缺点...\nStep 3: 选择最适合的技术栈...\nStep 4: 实现原型系统...\nStep 5: 测试和优化...\n==================================================\n\n[等待人工输入...]\n请审核上面的计划，是否同意执行？ (approved/rejected): _\n```\n\n如果你输入 `approved`，则继续执行 Act Crew；\n如果你输入 `rejected`，则重新生成计划。\n\n## 和 VS Code Plan/Act 的对比\n\n| VS Code Cline 插件 | CrewAI 实现 |\n|-------------------|------------|\n| Plan Mode（AI 生成计划） | `@start()` → Plan Crew |\n| 人工阅读计划，切换 Act | `@human_feedback` 暂停等待 |\n| Act Mode（AI 执行计划） | `@listen(\"approved\")` → Act Crew |\n| 返回 Plan 修改 | `@listen(\"rejected\")` → 重新规划 |\n\n\n\n实现 Plan → Act 模式最简单的组合是：\n\n| 组件 | 作用 |\n|------|------|\n| **Flow** | 编排整个流程 |\n| **`@human_feedback`** | 暂停等待人工审核 |\n| **`@router`** | 根据审核结果走不同分支 |\n| **多个 Crew** | 一个负责规划，一个负责执行 |\n\n需要我切换到 ACT MODE 帮你用这个模式改造当前项目，实际跑起来看看效果吗？","readmeExcerpt":"该项目的环境目录如下 ~/work/golang/crewai-agent 命令 source .venv/bin/activate 在此目录下执行 crewai 如何做到 像vscode 插件中的 plan. act 模式。 先plan. 人工确认后切到act 这个需求用 CrewAI 的 **Flow + @human_feedback + @router** 组合就可以实现。我给你设计一个完整的 Plan → Act 模式： 架构设计 完整代码示例 项目结构 1. Plan Crew（生成计划） **crews/plan_crew/config/agents.yaml**： **crews/plan_crew/config/tasks.yaml**： 2. Act Crew（执行计划） **crews/act_crew/config/agents.yaml**： **crews/act_crew/config/tasks.","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"### 方式一：用 crewai CLI（推荐）\n### 构建虚拟环境\nuv venv 是 Python 包管理工具 uv 提供的命令，用于创建 Python 虚拟环境。\nuv venv {{虚拟环境名称}}\nuv venv {{虚拟环境名称}} --python 3.12 ##指定python 版本\n ### 启动虚拟环境\nsource .venv/bin/activate\n### 虚拟环境内执行\nuv pip install crewai \n### 创建项目\ncrewai create crew hello-agent\n\n\n\n# 先在项目根目录安装依赖\nuv sync\n\n# 然后运行\nuv run\n\n## 退出虚拟环境\n\ndeactivate"},{"language":"text","snippet":"@start()\n            │\n            ▼\n    ┌─────────────────┐\n    │  Plan Crew       │  ← AI 先生成计划\n    │  (planner agent) │\n    └────────┬────────┘\n             │ 输出计划\n             ▼\n    ┌─────────────────┐\n    │  @human_feedback │  ← 展示计划给人类，等待确认\n    │   \"请审核该计划\"  │\n    └────────┬────────┘\n             │\n      ┌──────┴──────┐\n      ▼              ▼\n  \"approved\"     \"rejected\"\n      │              │\n      ▼              ▼\n┌──────────┐  ┌──────────┐\n│ Act Crew  │  │ 返回修改  │\n│ 执行计划  │  │ 重新规划  │\n└──────────┘  └──────────┘"},{"language":"text","snippet":"src/my_flow/\n├── crews/\n│   ├── plan_crew/            # Plan Crew\n│   │   ├── config/\n│   │   │   ├── agents.yaml\n│   │   │   └── tasks.yaml\n│   │   └── plan_crew.py\n│   └── act_crew/             # Act Crew\n│       ├── config/\n│       │   ├── agents.yaml\n│       │   └── tasks.yaml\n│       └── act_crew.py\n├── main.py                   # Flow 编排\n└── flow.py                   # Plan → Act 流程"},{"language":"yaml","snippet":"planner:\n  role: >\n    {topic} Strategy Planner\n  goal: >\n    Create a detailed step-by-step plan for {topic}\n  backstory: >\n    You're a strategic planner who breaks down complex topics\n    into actionable steps. Known for your clear and structured plans."},{"language":"yaml","snippet":"planning_task:\n  description: >\n    Create a detailed plan for: {topic}\n    Break it down into clear, actionable steps.\n    Consider timeline, resources needed, and potential risks.\n  expected_output: >\n    A detailed plan with 5-10 steps, each step including:\n    - What needs to be done\n    - Expected outcome\n    - Dependencies (if any)\n    Format as markdown.\n  agent: planner"},{"language":"yaml","snippet":"executor:\n  role: >\n    {topic} Execution Specialist\n  goal: >\n    Execute the approved plan for {topic} step by step\n  backstory: >\n    You're a reliable executor who follows plans precisely.\n    You complete each step thoroughly before moving to the next."}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"crewai 框架应用 该项目的环境目录如下 ~/work/golang/crewai-agent 命令 source .venv/bin/activate 在此目录下执行 crewai 如何做到 像vscode 插件中的 plan. act 模式。 先plan. 人工确认后切到act 这个需求用 CrewAI 的 **Flow + @human_feedback + @router** 组合就可以实现。我给你设计一个完整的 Plan → Act 模式： 架构设计 完整代码示例 项目结构 1. Plan Crew（生成计划） **crews/plan_crew/config/agents.yaml**： **crews/plan_crew/config/tasks.yaml**： 2. Act Crew（执行计划） **crews/act_crew/config/agents.yaml**： **crews/act_crew/config/tasks.","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":352,"uniquenessScore":64,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T18:18:12.050Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T18:18:12.050Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T03:52:43.071Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}