{"id":"8b3120e2-c3ff-41cc-9084-3e45d4b3166d","entityType":"agent","slug":"crewai-myriem-ea-dermaguard","name":"Dermaguard","canonicalUrl":"https://www.xpersona.co/agent/crewai-myriem-ea-dermaguard","canonicalPath":"/agent/crewai-myriem-ea-dermaguard","generatedAt":"2026-10-10T00:58:34.338Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T20:05:57.407Z","emptyReason":null},"description":"Multi-agent dermatological triage system using ResNet-50 and CrewAI for skin lesion classification 🩺 DermaGuard UIR **Multi-Agent AI System for Skin Lesion Triage** *\"The goal is not to build the most complex system. It is to build a system where every component exists for a reason, every agent has a job, and you can explain why.\"* — --- 📌 Overview DermaGuard is a multi-agent AI system that classifies skin lesion images as **Benign**, **Malignant**, or **Suspicious** using a fine-tuned ResNet-50 CNN, generates a","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/myriem-ea/Dermaguard","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/myriem-ea/Dermaguard","kind":"source"}],"safetyScore":66,"overallRank":18.2,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Multi-agent dermatological triage system using ResNet-50 and CrewAI for skin lesion classification 🩺 DermaGuard UIR **Multi-Agent AI System for Skin Lesion Tri"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:05:57.407Z","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":"2026-10-09T20:05:57.407Z","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":"2026-10-09T20:05:57.401Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T20:05:57.407Z","lastCrawledAt":"2026-10-09T20:05:57.401Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T20:05:57.401Z","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-myriem-ea-dermaguard/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T00:58:34.338Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-myriem-ea-dermaguard/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":"2026-10-09T20:05:57.407Z","emptyReason":null},"readme":"# 🩺 DermaGuard UIR\n**Multi-Agent AI System for Skin Lesion Triage**\n\n> *\"The goal is not to build the most complex system. It is to build a system where every component exists for a reason, every agent has a job, and you can explain why.\"* —\n\n---\n\n## 📌 Overview\n\nDermaGuard is a multi-agent AI system that classifies skin lesion images as **Benign**, **Malignant**, or **Suspicious** using a fine-tuned ResNet-50 CNN, generates a structured clinical report via OpenAI GPT-4o-mini, and enforces mandatory human approval before saving anything.\n\nBuilt for the **S8 Integrated Project — Building Multi-Agent AI Systems**\nUIR · AI & Big Data Program · 2025–2026\n\n---\n\n## 🏗️ Architecture\nSkin Lesion Image\n↓\n🧠 Agent 3 — Orchestrator      (coordinates · logs · handles errors)\n↓\n🔬 Agent 1 — CNN Classifier    (ResNet-50 · ISIC HAM10000)\n↓\n📝 Agent 2 — Report Generator  (OpenAI GPT-4o-mini · 5-section report)\n↓\n👨‍⚕️ Human-in-the-Loop          (approve · reject · revise)\n↓\n✅ Approved Clinical Report    (saved to outputs/)\n\n---\n\n## ⚙️ Tech Stack\n\n| Component | Technology |\n|---|---|\n| Agent Framework | CrewAI |\n| LLM Backend | OpenAI GPT-4o-mini |\n| Deep Learning | PyTorch ≥ 2.0 · ResNet-50 |\n| Dataset | HAM10000 / ISIC Archive (10k images) |\n| Web Interface | Flask · HTML/CSS/JS |\n| Language | Python 3.11 |\n\n---\n\n## 📁 Project Structure\n\ndermaguard/\n├── main.py                  # CLI entry point\n├── app.py                   # Flask web server\n├── dermaguard_uir.html      # Clinical web interface\n├── config.py                # All settings and paths\n├── requirements.txt         # Dependencies\n├── prepare_data.py          # Organizes HAM10000 dataset\n├── .env.example             # Environment template\n│\n├── agents/\n│   ├── orchestrator.py      # Agent 3 — coordinates pipeline\n│   ├── classifier_agent.py  # Agent 1 — CNN classifier\n│   └── report_agent.py      # Agent 2 — report generator\n│\n├── tools/\n│   ├── cnn_tool.py          # ResNet-50 wrapped as CrewAI tool\n│   ├── report_tool.py       # OpenAI report generation\n│   └── hitl_tool.py         # Human-in-the-loop checkpoint\n│\n├── model/\n│   ├── model_def.py         # ResNet-50 architecture\n│   ├── train.py             # Training script\n│   └── evaluate.py          # Metrics + confusion matrix\n│\n└── data/\n├── dataset.py           # ISIC dataset loader\n└── transforms.py        # Data augmentation pipeline\n\n---\n\n## 🚀 Setup & Installation\n\n### 1. Clone the repository\n```bash\ngit clone https://github.com/tahaelqassid/DermaGuard.git\ncd DermaGuard\n```\n\n### 2. Create virtual environment\n```bash\n# Windows\npython -m venv venv\nvenv\\Scripts\\activate\n\n# Mac/Linux\npython3 -m venv venv\nsource venv/bin/activate\n```\n\n### 3. Install dependencies\n```bash\npip install -r requirements.txt\n```\n\n### 4. Configure environment\n```bash\ncp .env.example .env\n```\nEdit `.env` and add your OpenAI API key:\nOPENAI_API_KEY=your_key_here\nOPENAI_MODEL_NAME=gpt-4o-mini\n\n---\n\n## 📦 Dataset Setup\n\nDownload **HAM10000** from [Kaggle](https://www.kaggle.com/datasets/kmader/skin-cancer-mnist-ham10000) and extract to a folder, then run:\n\n```bash\npython prepare_data.py\n```\n\nExpected output:\ntrain/benign:     5570 images\ntrain/malignant:  1301 images\ntrain/suspicious: 1141 images\nval/benign:        887 images\nval/malignant:     326 images\nval/suspicious:    285 images\n\n---\n\n## 🧠 Train the Model\n\n```bash\npython model/train.py\n```\n\n- ResNet-50 fine-tuned on HAM10000\n- 15 epochs · batch size 32 · AdamW optimizer\n- Class weights [1.0, 5.0, 4.0] for imbalance correction\n- Best model saved to `model/dermaguard_cnn.pth`\n\n---\n\n## 📊 Evaluate the Model\n\n```bash\npython model/evaluate.py\n```\n\n| Metric | Value |\n|---|---|\n| Validation Accuracy | 80.0% |\n| Malignant Recall | 44% |\n| Macro F1 | 0.66 |\n| Benign F1 | 0.90 |\n\nConfusion matrix saved to `outputs/confusion_matrix.png`\n\n---\n\n## 🖥️ Run the Web Interface\n\n```bash\npython app.py\n```\n\nOpen your browser at: **http://localhost:5000**\n\nFeatures:\n- Upload skin lesion image (JPEG, PNG, TIFF, BMP)\n- Live agent pipeline visualization\n- Real CNN classification with probability bars\n- Structured 5-section clinical report\n- Human approval checkpoint (Approve / Reject / Revise)\n- Download approved report as `.txt`\n- Session history tracking\n\n---\n\n## 💻 Run via CLI\n\n```bash\npython main.py path/to/image.jpg\n```\n\n---\n\n## 📋 Minimum Requirements Met\n\n- ✅ 2 specialist agents + 1 orchestrator\n- ✅ PyTorch CNN trained on HAM10000 with evaluation\n- ✅ DL model wrapped as functional CrewAI tool\n- ✅ Human-in-the-loop checkpoint with revision loop\n- ✅ Error handling — no crashes\n- ✅ JSON logging with UTC timestamps\n- ✅ Web interface with clinical dashboard\n- ✅ Reproducible setup via this README\n\n---\n\n\n\n\n\n\n**Program:** AI & Big Data · UIR · S8 · 2025–2026\n\n---\n","readmeExcerpt":"🩺 DermaGuard UIR **Multi-Agent AI System for Skin Lesion Triage** *\"The goal is not to build the most complex system. It is to build a system where every component exists for a reason, every agent has a job, and you can explain why.\"* — --- 📌 Overview DermaGuard is a multi-agent AI system that classifies skin lesion images as **Benign**, **Malignant**, or **Suspicious** using a fine-tuned ResNet-50 CNN, generates a","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"git clone https://github.com/tahaelqassid/DermaGuard.git\ncd DermaGuard"},{"language":"bash","snippet":"# Windows\npython -m venv venv\nvenv\\Scripts\\activate\n\n# Mac/Linux\npython3 -m venv venv\nsource venv/bin/activate"},{"language":"bash","snippet":"pip install -r requirements.txt"},{"language":"bash","snippet":"cp .env.example .env"},{"language":"bash","snippet":"python prepare_data.py"},{"language":"bash","snippet":"python model/train.py"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Multi-agent dermatological triage system using ResNet-50 and CrewAI for skin lesion classification 🩺 DermaGuard UIR **Multi-Agent AI System for Skin Lesion Triage** *\"The goal is not to build the most complex system. It is to build a system where every component exists for a reason, every agent has a job, and you can explain why.\"* — --- 📌 Overview DermaGuard is a multi-agent AI system that classifies skin lesion images as **Benign**, **Malignant**, or **Suspicious** using a fine-tuned ResNet-50 CNN, generates a","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":370,"uniquenessScore":67,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:05:57.407Z","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":"2026-10-09T20:05:57.407Z","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":"2026-10-10T00:58:34.338Z","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"}]}}}