{"id":"c6122c16-db7f-418d-8b96-4f39ec4cd7df","entityType":"agent","slug":"crewai-sakshi3027-ai-agents","name":"AI_agents","canonicalUrl":"https://www.xpersona.co/agent/crewai-sakshi3027-ai-agents","canonicalPath":"/agent/crewai-sakshi3027-ai-agents","generatedAt":"2026-10-09T00:24:24.358Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-06-01T00:30:47.945Z","emptyReason":null},"description":"Multi-agent AI system for automated data analysis using CrewAI & GPT-4. Features intelligent agents for EDA, visualization, and report generation. AutoAnalyst: Multi-Agent Data Science Assistant An intelligent multi-agent system that autonomously performs end-to-end data analysis, ML model training, and report generation — powered by CrewAI and GPT-4. --- What It Does You upload any CSV file. The system automatically: - Analyzes the data (EDA, statistics, correlations) - Trains and compares multiple ML models - Generates interactive visualizations - Produces a","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 6/1/2026.","installCommand":"git clone https://github.com/Sakshi3027/AI_agents.git","sourceUrl":"https://github.com/Sakshi3027/AI_agents","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/Sakshi3027/AI_agents","kind":"source"}],"safetyScore":66,"overallRank":20.8,"popularityScore":8,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Multi-agent AI system for automated data analysis using CrewAI & GPT-4. Features intelligent agents for EDA, visualization, and report generation. AutoAnalyst: "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-06-01T00:30:47.945Z","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":"GITHUB OPENCLEW","verified":false,"confidence":"medium","updatedAt":"2026-06-01T00:30:47.945Z","emptyReason":null},"stars":1,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"1 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-06-01T00:30:47.945Z","emptyReason":null},"lastUpdatedAt":"2026-06-01T00:30:47.945Z","lastCrawledAt":"2026-06-01T00:30:47.945Z","lastIndexedAt":null,"nextCrawlAt":"2026-06-08T00:30:47.945Z","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/Sakshi3027/AI_agents.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-sakshi3027-ai-agents/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T00:24:24.357Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-sakshi3027-ai-agents/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":"2026-06-01T00:30:47.945Z","emptyReason":null},"readme":"# AutoAnalyst: Multi-Agent Data Science Assistant\n\nAn intelligent multi-agent system that autonomously performs end-to-end data analysis, ML model training, and report generation — powered by CrewAI and GPT-4.\n\n---\n\n## What It Does\n\nYou upload any CSV file. The system automatically:\n- Analyzes the data (EDA, statistics, correlations)\n- Trains and compares multiple ML models\n- Generates interactive visualizations\n- Produces a full written report\n\nNo manual steps. No code required from the end user.\n\n---\n\n## System Architecture\n\nThe system is organized into 5 phases, each adding a new layer of capability:\n\n**Phase 1 — Data Analysis Pipeline**\n5 specialized AI agents run sequentially, each passing output to the next:\n1. Data Loader Agent — validates data quality and structure\n2. EDA Specialist Agent — performs statistical analysis\n3. Visualization Expert Agent — generates and interprets charts\n4. Insights Analyst Agent — identifies patterns and recommendations\n5. Report Writer Agent — produces a professional markdown report\n\n**Phase 2 — Machine Learning Pipeline**\n4 ML agents handle automated modeling:\n- Feature Engineer Agent — selects and transforms features\n- Model Selector Agent — chooses appropriate algorithms\n- Model Trainer Agent — trains Logistic Regression, Decision Tree, Random Forest, Gradient Boosting\n- Model Evaluator Agent — compares models on Accuracy, Precision, Recall, F1, ROC-AUC\n\n**Phase 3 — Streamlit Web Dashboard**\nInteractive UI built with Streamlit:\n- Drag-and-drop CSV upload\n- Real-time data exploration with Plotly charts\n- One-click ML model training with live progress\n- Results dashboard with model comparison and feature importance\n\n**Phase 4 — Advanced ML**\n- AutoML with Optuna for hyperparameter tuning — achieved 37.1% F1 improvement (0.30 to 0.41)\n- SHAP explainability — shows why the model made each prediction\n- Ensemble methods — Voting and Stacking classifiers\n\n**Phase 5 — Production API**\n- FastAPI REST API deployed on Render.com\n- Docker containerized for consistent deployment\n- Swagger UI documentation at `/docs`\n- Response time under 200ms\n- Supports single prediction and batch CSV prediction\n\n---\n\n## ML Results (Healthcare Dataset)\n\nTrained and evaluated on 500 patient records predicting heart disease:\n\n| Model               | Accuracy | F1-Score | ROC-AUC |\n|---------------------|----------|----------|---------|\n| Logistic Regression | 0.75     | 0.67     | 0.82    |\n| Decision Tree       | 0.72     | 0.64     | 0.78    |\n| Random Forest       | 0.81     | 0.75     | 0.88    |\n| Gradient Boosting   | 0.79     | 0.72     | 0.86    |\n\n**Best Model:** Random Forest — auto-selected based on F1-Score\n\n**Top Predictors (via SHAP):** Cholesterol, Age, Blood Pressure\n\n**AutoML Result:** Random Forest F1 improved from 0.30 to 0.41 (+37.1%) using Optuna\n\n---\n\n## API Endpoints\n\n| Method | Endpoint        | Description                        |\n|--------|-----------------|------------------------------------|\n| GET    | /               | Welcome message and API info       |\n| GET    | /health         | Health check and model status      |\n| POST   | /predict        | Single patient prediction          |\n| POST   | /batch-predict  | Batch predictions from CSV         |\n| GET    | /stats          | Usage statistics                   |\n| GET    | /model-info     | Model details and features         |\n| GET    | /docs           | Interactive Swagger UI             |\n\nLive API: `https://autoanalyst-api.onrender.com`\n\n---\n\n## Tech Stack\n\n| Layer          | Technology                                      |\n|----------------|-------------------------------------------------|\n| AI Agents      | CrewAI                                          |\n| Language Model | OpenAI GPT-4o-mini                              |\n| ML             | Scikit-learn, XGBoost, LightGBM                 |\n| AutoML         | Optuna                                          |\n| Explainability | SHAP                                            |\n| API            | FastAPI                                         |\n| Frontend       | Streamlit                                       |\n| Visualization  | Plotly, Matplotlib, Seaborn                     |\n| Data           | Pandas, NumPy                                   |\n| Deployment     | Docker, Docker Compose, Render.com              |\n| CI/CD          | GitHub Actions                                  |\n| Language       | Python 3.12                                     |\n\n---\n\n## Screenshots\n\n### Web Dashboard\n\n#### Home Page\n![Home](screenshots/streamlit_home.png)\n\n#### ML Training in Progress\n![Training](screenshots/streamlit_training.png)\n\n#### Model Performance Table\n![Performance](screenshots/streamlit_performance.png)\n\n#### Results & Insights\n![Results](screenshots/streamlit_results.png)\n\n---\n\n### Data Analysis Outputs\n\n#### Distribution Analysis\n![Distributions](screenshots/distributions.png)\n\n#### Correlation Heatmap\n![Correlation](screenshots/correlation_heatmap.png)\n\n#### Categorical Analysis\n![Categorical](screenshots/categorical_distributions.png)\n\n---\n\n### ML Results\n\n#### Model Performance Comparison\n![Model Comparison](screenshots/model_comparison.png)\n\n#### Confusion Matrices\n![Confusion Matrices](screenshots/confusion_matrices.png)\n\n#### ROC Curves\n![ROC Curves](screenshots/roc_curves.png)\n\n#### Feature Importance (Random Forest)\n![Feature Importance](screenshots/feature_importance.png)\n\n#### Full Analysis Collage\n![Analysis Collage](screenshots/analysis_collage.png)\n\n---\n\n## Quick Start\n\n### Prerequisites\n- Python 3.8+\n- OpenAI API key\n\n### Installation\n\n```bash\ngit clone https://github.com/Sakshi3027/AutoAnalyst.git\ncd AutoAnalyst\npython -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\ncp .env.example .env\n# Add your OPENAI_API_KEY to .env\n```\n\n### Run the Web Dashboard (Recommended)\n```bash\nstreamlit run streamlit_app.py\n```\nOpens at `http://localhost:8501`\n\n**Steps:**\n1. Click \"Load Sample Data\" in the sidebar\n2. Go to \"Data Analysis\" to explore\n3. Go to \"ML Pipeline\" and click \"Train Models\"\n4. View \"Results\" for full analysis\n\n### Run Data Analysis Only\n```bash\npython main.py\n```\nOutput: `outputs/analysis_report.md`\n\n### Run ML Pipeline Only\n```bash\npython main_ml.py\n```\nOutput: `outputs/ml_analysis_report.md` and `outputs/best_model.pkl`\n\n### Run Advanced ML (AutoML + SHAP)\n```bash\npython main_advanced.py\n```\n\n---\n\n## Docker Deployment\n\n```bash\n# Build\ndocker build -t autoanalyst .\n\n# Run\ndocker run -p 8000:8000 --env-file .env autoanalyst\n\n# Or with docker-compose\ndocker-compose up -d\n```\n\n---\n\n## Use Saved Model\n\n```python\nimport joblib\nimport pandas as pd\n\nmodel = joblib.load('outputs/best_model.pkl')\n\nnew_patient = pd.DataFrame({\n    'age': [55],\n    'bmi': [28.5],\n    'blood_pressure_systolic': [140],\n    'blood_pressure_diastolic': [90],\n    'cholesterol': [220],\n    'glucose': [120],\n    'exercise_hours_per_week': [3],\n    'gender_Male': [1],\n    'smoker_Yes': [1]\n})\n\nprediction = model.predict(new_patient)\nprobability = model.predict_proba(new_patient)\n\nprint(f\"Prediction: {'Heart Disease' if prediction[0] == 1 else 'No Heart Disease'}\")\nprint(f\"Probability: {probability[0][1]:.2%}\")\n```\n\n---\n\n## Project Structure\n\n```\nAI_agents/\n├── agents/                        # 12 AI agent definitions\n│   ├── data_loader_agent.py\n│   ├── eda_agent.py\n│   ├── visualization_agent.py\n│   ├── insight_agent.py\n│   ├── report_agent.py\n│   ├── feature_engineer_agent.py\n│   ├── model_selector_agent.py\n│   ├── model_trainer_agent.py\n│   ├── model_evaluator_agent.py\n│   ├── automl_agent.py\n│   ├── explainability_agent.py\n│   └── deep_learning_agent.py\n├── utils/\n│   ├── data_utils.py              # EDA and visualization helpers\n│   └── ml_utils.py                # ML training and evaluation\n├── data/\n│   └── healthcare_data.csv        # Sample dataset (500 records)\n├── outputs/                       # Generated reports and models\n├── screenshots/                   # UI screenshots\n├── api.py                         # FastAPI REST API\n├── Dockerfile\n├── docker-compose.yml\n├── main.py                        # Phase 1 pipeline\n├── main_ml.py                     # Phase 2 ML pipeline\n├── main_advanced.py               # Phase 4 advanced ML\n├── streamlit_app.py               # Phase 3 web dashboard\n├── requirements.txt\n└── README.md\n```\n\n---\n\n## Key Achievements\n\n- 12 AI agents for fully automated data science pipeline\n- 37.1% F1-Score improvement through AutoML (Optuna)\n- Production API deployed on Render.com with under 200ms response time\n- SHAP explainability for model transparency\n- Full Docker containerization\n- End-to-end: raw CSV in, trained model + report out\n\n---\n\n## Use Cases\n\n- Healthcare data analysis and prediction\n- Financial report generation\n- Marketing analytics\n- Research data exploration\n- Enterprise data science automation\n\n---\n\n## Author\n\n**Sakshi Chavan**\n- GitHub: [github.com/Sakshi3027](https://github.com/Sakshi3027)\n- Live API: [autoanalyst-api.onrender.com](https://autoanalyst-api.onrender.com)\n\n---\n\n## License\n\nMIT License","readmeExcerpt":"AutoAnalyst: Multi-Agent Data Science Assistant An intelligent multi-agent system that autonomously performs end-to-end data analysis, ML model training, and report generation — powered by CrewAI and GPT-4. --- What It Does You upload any CSV file. The system automatically: - Analyzes the data (EDA, statistics, correlations) - Trains and compares multiple ML models - Generates interactive visualizations - Produces a ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"git clone https://github.com/Sakshi3027/AutoAnalyst.git\ncd AutoAnalyst\npython -m venv venv\nsource venv/bin/activate\npip install -r requirements.txt\ncp .env.example .env\n# Add your OPENAI_API_KEY to .env"},{"language":"bash","snippet":"streamlit run streamlit_app.py"},{"language":"bash","snippet":"python main.py"},{"language":"bash","snippet":"python main_ml.py"},{"language":"bash","snippet":"python main_advanced.py"},{"language":"bash","snippet":"# Build\ndocker build -t autoanalyst .\n\n# Run\ndocker run -p 8000:8000 --env-file .env autoanalyst\n\n# Or with docker-compose\ndocker-compose up -d"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Multi-agent AI system for automated data analysis using CrewAI & GPT-4. Features intelligent agents for EDA, visualization, and report generation. AutoAnalyst: Multi-Agent Data Science Assistant An intelligent multi-agent system that autonomously performs end-to-end data analysis, ML model training, and report generation — powered by CrewAI and GPT-4. --- What It Does You upload any CSV file. The system automatically: - Analyzes the data (EDA, statistics, correlations) - Trains and compares multiple ML models - Generates interactive visualizations - Produces a","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":380,"uniquenessScore":67,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-06-01T00:30:47.945Z","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":"2026-06-01T00:30:47.945Z","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":"2026-10-09T00:24:24.358Z","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"}]}}}