{"id":"577fcd92-254f-4a04-a7b5-ade2a972f346","entityType":"agent","slug":"crewai-afine907-smart-city-agent","name":"smart-city-agent","canonicalUrl":"https://www.xpersona.co/agent/crewai-afine907-smart-city-agent","canonicalPath":"/agent/crewai-afine907-smart-city-agent","generatedAt":"2026-10-09T00:20:29.227Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-05-31T06:18:16.192Z","emptyReason":null},"description":"CrewAI Multi-Agent Traffic Signal Control — LLM-powered ±10s timing adjustment for smart city intersections Smart City Agent **用 CrewAI 多 Agent + LLM 让红绿灯更智慧，让城市交通更人性化** $1 $1 $1 --- 我们尝试引入 LLM 辅助红绿灯变得更加智慧聪明。每个路口有一个 Agent 负责观察和决策，多个 Agent 通过协调机制配合工作，让城市的交通更加人性化。 --- 多 Agent 架构 基于 $1 框架，每个路口由一个独立的 Agent 控制，多个 Agent 协同工作： **协调流程：** 1. 每个 Intersection Agent 观察路况，独立做出信号灯决策 2. ConflictDetector 检测相邻路口的相位冲突 3. Coordinator Agent 通过 LLM 推理协调冲突（紧急优先、排队优先） 4. 执行协调后的最终决策 --- Quick Start --- Benchmark 结果 早高峰场景（3x3 路口网格）： | 指标 | 固定配时 |","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 5/31/2026.","installCommand":"git clone https://github.com/afine907/smart-city-agent.git","sourceUrl":"https://github.com/afine907/smart-city-agent","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/afine907/smart-city-agent","kind":"source"}],"safetyScore":66,"overallRank":29.4,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"CrewAI Multi-Agent Traffic Signal Control — LLM-powered ±10s timing adjustment for smart city intersections Smart City Agent **用 CrewAI 多 Agent + LLM 让红绿灯更智慧，让城"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-05-31T06:18:16.192Z","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":"2026-05-31T06:18:16.192Z","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":"2026-05-31T06:18:16.192Z","emptyReason":null},"lastUpdatedAt":"2026-05-31T06:18:16.192Z","lastCrawledAt":"2026-05-31T06:18:16.192Z","lastIndexedAt":null,"nextCrawlAt":"2026-06-07T06:18:16.192Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/afine907/smart-city-agent.git","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-afine907-smart-city-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T00:20:29.227Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-afine907-smart-city-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 OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-05-31T06:18:16.192Z","emptyReason":null},"readme":"# Smart City Agent\n\n> **用 CrewAI 多 Agent + LLM 让红绿灯更智慧，让城市交通更人性化**\n\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Tests](https://img.shields.io/badge/tests-267%20passed-brightgreen.svg)](tests/)\n\n---\n\n我们尝试引入 LLM 辅助红绿灯变得更加智慧聪明。每个路口有一个 Agent 负责观察和决策，多个 Agent 通过协调机制配合工作，让城市的交通更加人性化。\n\n---\n\n## 多 Agent 架构\n\n基于 [CrewAI](https://github.com/crewAIInc/crewAI) 框架，每个路口由一个独立的 Agent 控制，多个 Agent 协同工作：\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│                    CrewAI Multi-Agent System                    │\n├─────────────────────────────────────────────────────────────────┤\n│                                                                 │\n│   ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    │\n│   │  Agent: 北路口 │    │  Agent: 东路口 │    │  Agent: 南路口 │    │\n│   │  观察路况      │    │  观察路况      │    │  观察路况      │    │\n│   │  LLM 推理决策  │    │  LLM 推理决策  │    │  LLM 推理决策  │    │\n│   └───────┬──────┘    └───────┬──────┘    └───────┬──────┘    │\n│           │                   │                   │            │\n│           │    ┌──────────────┴──────────────┐    │            │\n│           │    │                             │    │            │\n│           ▼    ▼                             ▼    ▼            │\n│   ┌───────────────────────────────────────────────────────┐   │\n│   │              ConflictDetector                         │   │\n│   │  检测相邻路口的相位冲突                                 │   │\n│   └───────────────────────────┬───────────────────────────┘   │\n│                               │                               │\n│                               ▼                               │\n│   ┌───────────────────────────────────────────────────────┐   │\n│   │              Coordinator Agent                         │   │\n│   │  收集各路口决策 → LLM 推理协调 → 输出最终方案           │   │\n│   └───────────────────────────────────────────────────────┘   │\n│                                                                 │\n└─────────────────────────────────────────────────────────────────┘\n```\n\n**协调流程：**\n\n1. 每个 Intersection Agent 观察路况，独立做出信号灯决策\n2. ConflictDetector 检测相邻路口的相位冲突\n3. Coordinator Agent 通过 LLM 推理协调冲突（紧急优先、排队优先）\n4. 执行协调后的最终决策\n\n---\n\n## Quick Start\n\n```bash\n# 克隆 + 安装\ngit clone https://github.com/afine907/smart-city-agent.git\ncd smart-city-agent\npip install -e .\n\n# 单路口仿真（规则引擎）\npython -m traffic_agent.cli run --steps 200\n\n# 多 Agent 仿真（CrewAI）\npython -m traffic_agent.cli run --steps 200 --multi-agent\n\n# 基准对比\npython -m traffic_agent.cli benchmark --steps 300 --scenario morning_peak\n```\n\n---\n\n## Benchmark 结果\n\n早高峰场景（3x3 路口网格）：\n\n| 指标 | 固定配时 | 规则引擎 | 改进 |\n|------|---------|---------|------|\n| 平均等待 (s) | 24.8 | 22.6 | **-8.8%** |\n| 吞吐量 (/s) | 2.44 | 2.39 | -2.2% |\n\n事故场景：\n\n| 指标 | 固定配时 | 规则引擎 | 改进 |\n|------|---------|---------|------|\n| 平均等待 (s) | 22.0 | 23.3 | -5.9% |\n| 吞吐量 (/s) | 1.60 | 1.79 | **+11.7%** |\n\n---\n\n## 内置场景\n\n| 场景 | 说明 |\n|------|------|\n| `morning_peak` | 早高峰，南北方向重 |\n| `evening_peak` | 晚高峰，东西方向重 |\n| `normal` | 平峰，各方向均衡 |\n| `pedestrian_heavy` | 行人高峰 |\n| `accident` | 事故，救护车频繁 |\n| `bicycle_rush` | 非机动车高峰 |\n\n```bash\npython -m traffic_agent.cli run --scenario morning_peak --steps 300\npython -m traffic_agent.cli scenarios\n```\n\n---\n\n## 项目结构\n\n```\nsrc/traffic_agent/\n├── simulation/\n│   ├── signal_controller.py   # 信号控制器 + 基线配时\n│   ├── detector.py            # 检测器模型 + 趋势分析\n│   ├── scenarios.py           # 交通场景定义\n│   ├── sim_loop.py            # 仿真主循环\n│   └── grid.py                # 3×3 网格仿真 (CrewAI)\n├── crew/\n│   ├── traffic_crew.py        # CrewAI 多 Agent 编排\n│   └── coordination.py        # 冲突检测 + 绿波协调 + 优先级解决\n├── tools/\n│   └── traffic_tools.py       # CrewAI @tool 工具 (6 个)\n├── llm/\n│   ├── client.py              # LLM 客户端\n│   ├── parser.py              # 决策解析\n│   └── prompts.py             # Prompt 模板\n├── optimization/\n│   ├── rule_engine.py         # 规则引擎\n│   ├── layered.py             # 3 级决策管道\n│   └── cache.py               # 决策缓存\n├── comparison/\n│   └── benchmark.py           # 基准对比\n└── cli.py                     # CLI 入口\n```\n\n---\n\n## 测试\n\n```bash\n# 运行全部测试（267 个）\npython -m pytest tests/ -v\n\n# CrewAI 多 Agent 测试\npython -m pytest tests/test_crew.py -v\n\n# 信号控制器测试\npython -m pytest tests/test_signal_controller.py -v\n\n# 规则引擎测试\npython -m pytest tests/test_timing_rules.py -v\n```\n\n---\n\n## LLM 配置\n\n```bash\nexport OPENAI_API_KEY=\"your-key\"\nexport OPENAI_API_BASE=\"https://api.openai.com/v1\"\n```\n\n---\n\n## License\n\nMIT License - 详见 [LICENSE](LICENSE)\n","readmeExcerpt":"Smart City Agent **用 CrewAI 多 Agent + LLM 让红绿灯更智慧，让城市交通更人性化** $1 $1 $1 --- 我们尝试引入 LLM 辅助红绿灯变得更加智慧聪明。每个路口有一个 Agent 负责观察和决策，多个 Agent 通过协调机制配合工作，让城市的交通更加人性化。 --- 多 Agent 架构 基于 $1 框架，每个路口由一个独立的 Agent 控制，多个 Agent 协同工作： **协调流程：** 1. 每个 Intersection Agent 观察路况，独立做出信号灯决策 2. ConflictDetector 检测相邻路口的相位冲突 3. Coordinator Agent 通过 LLM 推理协调冲突（紧急优先、排队优先） 4. 执行协调后的最终决策 --- Quick Start --- Benchmark 结果 早高峰场景（3x3 路口网格）： | 指标 | 固定配时 | ","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"┌─────────────────────────────────────────────────────────────────┐\n│                    CrewAI Multi-Agent System                    │\n├─────────────────────────────────────────────────────────────────┤\n│                                                                 │\n│   ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    │\n│   │  Agent: 北路口 │    │  Agent: 东路口 │    │  Agent: 南路口 │    │\n│   │  观察路况      │    │  观察路况      │    │  观察路况      │    │\n│   │  LLM 推理决策  │    │  LLM 推理决策  │    │  LLM 推理决策  │    │\n│   └───────┬──────┘    └───────┬──────┘    └───────┬──────┘    │\n│           │                   │                   │            │\n│           │    ┌──────────────┴──────────────┐    │            │\n│           │    │                             │    │            │\n│           ▼    ▼                             ▼    ▼            │\n│   ┌───────────────────────────────────────────────────────┐   │\n│   │              ConflictDetector                         │   │\n│   │  检测相邻路口的相位冲突                                 │   │\n│   └───────────────────────────┬───────────────────────────┘   │\n│                               │                               │\n│                               ▼                               │\n│   ┌───────────────────────────────────────────────────────┐   │\n│   │              Coordinator Agent                         │   │\n│   │  收集各路口决策 → LLM 推理协调 → 输出最终方案           │   │\n│   └───────────────────────────────────────────────────────┘   │\n│                                                                 │\n└─────────────────────────────────────────────────────────────────┘"},{"language":"bash","snippet":"# 克隆 + 安装\ngit clone https://github.com/afine907/smart-city-agent.git\ncd smart-city-agent\npip install -e .\n\n# 单路口仿真（规则引擎）\npython -m traffic_agent.cli run --steps 200\n\n# 多 Agent 仿真（CrewAI）\npython -m traffic_agent.cli run --steps 200 --multi-agent\n\n# 基准对比\npython -m traffic_agent.cli benchmark --steps 300 --scenario morning_peak"},{"language":"bash","snippet":"python -m traffic_agent.cli run --scenario morning_peak --steps 300\npython -m traffic_agent.cli scenarios"},{"language":"text","snippet":"src/traffic_agent/\n├── simulation/\n│   ├── signal_controller.py   # 信号控制器 + 基线配时\n│   ├── detector.py            # 检测器模型 + 趋势分析\n│   ├── scenarios.py           # 交通场景定义\n│   ├── sim_loop.py            # 仿真主循环\n│   └── grid.py                # 3×3 网格仿真 (CrewAI)\n├── crew/\n│   ├── traffic_crew.py        # CrewAI 多 Agent 编排\n│   └── coordination.py        # 冲突检测 + 绿波协调 + 优先级解决\n├── tools/\n│   └── traffic_tools.py       # CrewAI @tool 工具 (6 个)\n├── llm/\n│   ├── client.py              # LLM 客户端\n│   ├── parser.py              # 决策解析\n│   └── prompts.py             # Prompt 模板\n├── optimization/\n│   ├── rule_engine.py         # 规则引擎\n│   ├── layered.py             # 3 级决策管道\n│   └── cache.py               # 决策缓存\n├── comparison/\n│   └── benchmark.py           # 基准对比\n└── cli.py                     # CLI 入口"},{"language":"bash","snippet":"# 运行全部测试（267 个）\npython -m pytest tests/ -v\n\n# CrewAI 多 Agent 测试\npython -m pytest tests/test_crew.py -v\n\n# 信号控制器测试\npython -m pytest tests/test_signal_controller.py -v\n\n# 规则引擎测试\npython -m pytest tests/test_timing_rules.py -v"},{"language":"bash","snippet":"export OPENAI_API_KEY=\"your-key\"\nexport OPENAI_API_BASE=\"https://api.openai.com/v1\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"CrewAI Multi-Agent Traffic Signal Control — LLM-powered ±10s timing adjustment for smart city intersections Smart City Agent **用 CrewAI 多 Agent + LLM 让红绿灯更智慧，让城市交通更人性化** $1 $1 $1 --- 我们尝试引入 LLM 辅助红绿灯变得更加智慧聪明。每个路口有一个 Agent 负责观察和决策，多个 Agent 通过协调机制配合工作，让城市的交通更加人性化。 --- 多 Agent 架构 基于 $1 框架，每个路口由一个独立的 Agent 控制，多个 Agent 协同工作： **协调流程：** 1. 每个 Intersection Agent 观察路况，独立做出信号灯决策 2. ConflictDetector 检测相邻路口的相位冲突 3. Coordinator Agent 通过 LLM 推理协调冲突（紧急优先、排队优先） 4. 执行协调后的最终决策 --- Quick Start --- Benchmark 结果 早高峰场景（3x3 路口网格）： | 指标 | 固定配时 |","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":351,"uniquenessScore":64,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-05-31T06:18:16.192Z","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":"2026-05-31T06:18:16.192Z","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":"2026-10-09T00:20:29.227Z","emptyReason":null},"items":[{"id":"959108e7-5f7c-45ac-bea0-9ab67f017226","entityType":"agent","canonicalPath":"/agent/langchain-x1pay-langchain","slug":"langchain-x1pay-langchain","name":"@x1pay/langchain","description":"LangChain/LangGraph tools for AI agent x402 payments on X1","url":"https://www.npmjs.com/package/@x1pay/langchain","homepage":null,"source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:07.099Z","createdAt":"2026-05-23T06:52:58.553Z","downloads":null},{"id":"4f8f8f95-34f7-49a9-b516-391d1c355d6c","entityType":"agent","canonicalPath":"/agent/langchain-langchain-langgraph-swarm","slug":"langchain-langchain-langgraph-swarm","name":"@langchain/langgraph-swarm","description":"An implementation of a multi-agent swarm using LangGraph","url":"git+ssh://git@github.com/langchain-ai/langgraphjs.git","homepage":"https://github.com/langchain-ai/langgraphjs#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:03.792Z","createdAt":"2026-05-23T06:52:55.396Z","downloads":null},{"id":"e36fd59b-38d7-4e73-aa20-c1431a8f7434","entityType":"agent","canonicalPath":"/agent/langchain-langchain-langgraph-supervisor","slug":"langchain-langchain-langgraph-supervisor","name":"@langchain/langgraph-supervisor","description":"LangGraph Multi-Agent Supervisor","url":"git+ssh://git@github.com/langchain-ai/langgraphjs.git","homepage":"https://github.com/langchain-ai/langgraphjs#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:03.756Z","createdAt":"2026-05-23T06:52:55.353Z","downloads":null},{"id":"d1d0f93e-b722-4791-9bbf-2532470054c2","entityType":"agent","canonicalPath":"/agent/langchain-oceanbus-langchain","slug":"langchain-oceanbus-langchain","name":"oceanbus-langchain","description":"LangChain tools for OceanBus — give your LangChain and CrewAI agents a global identity, encrypted messaging, and Yellow Pages service discovery with a single import.","url":"git+https://github.com/oceanbus/oceanbus.git","homepage":"https://github.com/oceanbus/oceanbus#readme","source":"GITHUB_OPENCLEW","protocols":["OPENCLAW"],"capabilities":["oceanbus","langchain","langchain-tools","agent-to-agent","ai-agent","communication","messaging","e2ee","structured-tool","yellow-pages","service-discovery","reputation","crewai"],"safetyScore":70,"overallRank":65,"updatedAt":"2026-06-01T00:29:02.595Z","createdAt":"2026-05-23T06:52:54.240Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}