{"id":32395361,"url":"https://github.com/suhasramanand/predictive-reliability-platform","last_synced_at":"2026-04-08T23:32:59.237Z","repository":{"id":319352763,"uuid":"1078455430","full_name":"suhasramanand/predictive-reliability-platform","owner":"suhasramanand","description":"End-to-end predictive reliability platform with anomaly detection, auto-remediation, and comprehensive observability for microservices","archived":false,"fork":false,"pushed_at":"2025-10-18T20:38:02.000Z","size":9459,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-18T21:29:30.905Z","etag":null,"topics":["anomaly-detection","auto-remediation","chaos-engineering","devops","docker","fastapi","grafana","kubernetes","microservices","monitoring","observability","predictive-maintenance","prometheus","python","react","site-reliability","sre","typescript"],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/suhasramanand.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-17T19:02:13.000Z","updated_at":"2025-10-18T20:38:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"e07b4514-42eb-4725-ab4b-4f82f5b32106","html_url":"https://github.com/suhasramanand/predictive-reliability-platform","commit_stats":null,"previous_names":["suhasramanand/predictive-reliability-platform"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/suhasramanand/predictive-reliability-platform","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suhasramanand%2Fpredictive-reliability-platform","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suhasramanand%2Fpredictive-reliability-platform/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suhasramanand%2Fpredictive-reliability-platform/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suhasramanand%2Fpredictive-reliability-platform/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/suhasramanand","download_url":"https://codeload.github.com/suhasramanand/predictive-reliability-platform/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suhasramanand%2Fpredictive-reliability-platform/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31579054,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-08T14:31:17.711Z","status":"ssl_error","status_checked_at":"2026-04-08T14:31:17.202Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anomaly-detection","auto-remediation","chaos-engineering","devops","docker","fastapi","grafana","kubernetes","microservices","monitoring","observability","predictive-maintenance","prometheus","python","react","site-reliability","sre","typescript"],"created_at":"2025-10-25T06:21:05.777Z","updated_at":"2026-04-08T23:32:59.231Z","avatar_url":"https://github.com/suhasramanand.png","language":"TypeScript","readme":"# Predictive Reliability \u0026 Auto-Remediation Platform\n\nA comprehensive cloud-native system that monitors microservices, detects anomalies in real-time, and automatically remediates issues through intelligent policy-driven actions.\n\n## Overview\n\nThis platform demonstrates an end-to-end Site Reliability Engineering (SRE) solution featuring:\n\n- **Instrumented Microservices**: 3 production-ready services with built-in observability\n- **Real-time Anomaly Detection**: ML-based time-series analysis for proactive issue detection\n- **Automated Remediation**: Policy-driven engine that executes recovery actions automatically\n- **Complete Observability Stack**: Metrics (Prometheus), Logs (Loki), Traces (Jaeger)\n- **Live Dashboard**: Modern React UI for monitoring and control\n- **Chaos Engineering**: Built-in failure injection for testing resilience\n- **AI-Powered Intelligence**: LLM-driven root cause analysis, incident summarization, and remediation advice\n\n### Screenshots\n\n**Dashboard Overview**\n\n![Dashboard Overview](docs/screenshots/01-dashboard-overview.png)\n*Real-time system monitoring with service health, auto-remediation status, and quick access to observability tools*\n\n**Anomaly Detection**\n\n![Anomaly Detection](docs/screenshots/02-anomalies-detected.png)\n*Active anomalies detected with severity classification, confidence scores, and expected value ranges*\n\n**Auto-Remediation Actions**\n\n![Remediation Actions](docs/screenshots/03-remediation-actions.png)\n*Complete history of executed remediation actions with policy triggers and execution details*\n\n**Policy Configuration**\n\n![Policy Configuration](docs/screenshots/04-policy-configuration.png)\n*YAML-driven policy rules with configurable thresholds, actions, and cooldown periods*\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│                         Dashboard (React)                        │\n│                    http://localhost:3000                         │\n└────────────────────┬────────────────────────────────────────────┘\n                     │\n         ┌───────────┴───────────┐\n         │                       │\n         ▼                       ▼\n┌─────────────────┐    ┌──────────────────┐\n│ Anomaly Service │    │  Policy Engine   │\n│   Port 8080     │───▶│    Port 8081     │\n└────────┬────────┘    └────────┬─────────┘\n         │                      │\n         │                      ├──► Docker API (restart containers)\n         │                      └──► Alerts \u0026 Actions\n         │\n         ▼\n┌──────────────────────────────────────────┐\n│           Prometheus :9090                │\n│      (Scrapes metrics every 10s)         │\n└────┬─────────┬──────────┬────────────────┘\n     │         │          │\n     ▼         ▼          ▼\n┌─────────┐ ┌──────────┐ ┌──────────────┐\n│ Orders  │ │  Users   │ │  Payments    │\n│  :8001  │ │  :8002   │ │   :8003      │\n└─────────┘ └──────────┘ └──────────────┘\n     │         │          │\n     └─────────┴──────────┴──► Jaeger :16686 (Traces)\n                         │\n                         └──► Loki :3100 (Logs)\n```\n\n## Components\n\n### Microservices\n- **Orders Service** (Port 8001): Order management with chaos injection\n- **Users Service** (Port 8002): User account management\n- **Payments Service** (Port 8003): Payment processing\n\nEach service exposes:\n- `/health` - Health check endpoint\n- `/metrics` - Prometheus-format metrics\n- `/docs` - FastAPI Swagger documentation\n- Full OpenTelemetry instrumentation for distributed tracing\n\n### Anomaly Detection Service (Port 8080)\n- Pulls metrics from Prometheus every 30 seconds\n- Statistical anomaly detection using moving averages and standard deviation\n- Monitors: latency (p99), error rates, CPU usage\n- Classifies anomalies by severity: normal, info, warning, critical\n- REST API for predictions and health status\n\n### Policy \u0026 Auto-Remediation Engine (Port 8081)\n- YAML-based policy definitions\n- Continuous evaluation against detected anomalies\n- Actions: `restart_container`, `scale_up`, `alert`\n- Cooldown periods to prevent action spam\n- Complete action history tracking\n- Toggle for enabling/disabling auto-remediation\n\n### Dashboard (Port 3000)\n- **Overview**: System health, auto-remediation status\n- **Anomalies**: Real-time anomaly detection and predictions\n- **Actions**: Remediation action history\n- **Policies**: Active policy configurations\n\nSee [Dashboard Screenshots](#screenshots) above for visual examples.\n\n### Observability Stack\n- **Prometheus** (9090): Metrics collection and time-series database\n- **Grafana** (3001): Visualization and dashboards (admin/admin)\n- **Loki** (3100): Log aggregation\n- **Jaeger** (16686): Distributed tracing\n- **AI Service** (8090): LLM-powered intelligence (requires GROQ_API_KEY)\n\n**Monitoring Tools**\n\n![Grafana](docs/screenshots/05-grafana-dashboards.png)\n*Grafana Explore interface with Prometheus data source for metrics visualization*\n\n![Prometheus Targets](docs/screenshots/06-prometheus-targets.png)\n*Prometheus scrape targets showing all services health status*\n\n![Prometheus Metrics](docs/screenshots/07-prometheus-metrics.png)\n*Prometheus metrics query interface with time-series visualization*\n\n![Jaeger Tracing](docs/screenshots/08-jaeger-tracing.png)\n*Jaeger distributed tracing interface for trace analysis*\n\n### Chaos Simulator\nPython-based tool for injecting failures:\n- Random failures and latency spikes\n- Traffic generation and load testing\n- Chaos engineering experiments\n\nSee the [chaos_simulator/README.md](chaos_simulator/README.md) for detailed usage.\n\n### AI Service (Port 8090) - NEW\nLLM-powered intelligence layer using Groq API:\n- **Natural Language Queries**: Ask questions about your system in plain English\n- **Incident Summarization**: Auto-generate incident reports from metrics, logs, and traces\n- **Root Cause Analysis**: AI identifies likely failure subsystems from observability data\n- **Remediation Advice**: LLM recommends best corrective actions with rationale\n\n**Endpoints:**\n- `POST /chat` - General SRE Q\u0026A with context\n- `POST /summarize` - Generate incident summary from observability data\n- `POST /rca` - Root cause analysis from logs and metrics correlation\n- `POST /advice` - Remediation action recommendation\n\n**Configuration:**\nSet the `GROQ_API_KEY` environment variable to enable AI features. See [AI Configuration](#ai-configuration) below.\n\n## API Documentation\n\nAll services provide interactive OpenAPI (Swagger) documentation:\n\n**Anomaly Detection Service**\n\n![Anomaly API](docs/screenshots/09-anomaly-api-docs.png)\n*Anomaly detection REST API with endpoints for predictions, health checks, and manual detection*\n\n**Policy Engine**\n\n![Policy API](docs/screenshots/10-policy-api-docs.png)\n*Policy engine REST API for status, policy management, and remediation actions*\n\n**Microservices APIs**\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd width=\"33%\"\u003e\n      \u003cimg src=\"docs/screenshots/11-orders-service-docs.png\" alt=\"Orders API\" /\u003e\n      \u003cp align=\"center\"\u003e\u003ci\u003eOrders Service API\u003c/i\u003e\u003c/p\u003e\n    \u003c/td\u003e\n    \u003ctd width=\"33%\"\u003e\n      \u003cimg src=\"docs/screenshots/12-users-service-docs.png\" alt=\"Users API\" /\u003e\n      \u003cp align=\"center\"\u003e\u003ci\u003eUsers Service API\u003c/i\u003e\u003c/p\u003e\n    \u003c/td\u003e\n    \u003ctd width=\"33%\"\u003e\n      \u003cimg src=\"docs/screenshots/13-payments-service-docs.png\" alt=\"Payments API\" /\u003e\n      \u003cp align=\"center\"\u003e\u003ci\u003ePayments Service API\u003c/i\u003e\u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n## Quick Start\n\n### Prerequisites\n- Docker \u0026 Docker Compose\n- Python 3.11+ (for chaos simulator)\n- 8GB+ RAM recommended\n- Ports available: 3000, 3001, 8001-8003, 8080-8081, 9090, 16686\n\n### 1. Start the Platform\n\n```bash\n# Clone or navigate to the project\ncd predictive-reliability-platform\n\n# Start all services\nmake up\n\n# This will start:\n# - 3 Microservices\n# - Anomaly Detection Service\n# - Policy Engine\n# - Dashboard\n# - Prometheus, Grafana, Loki, Jaeger\n```\n\nWait 30-60 seconds for all services to initialize.\n\n### 2. Access the Interfaces\n\n- **Dashboard**: http://localhost:3000\n- **Grafana**: http://localhost:3001 (admin/admin)\n- **Prometheus**: http://localhost:9090\n- **Jaeger**: http://localhost:16686\n- **Anomaly API Docs**: http://localhost:8080/docs\n- **Policy Engine API Docs**: http://localhost:8081/docs\n- **AI Service API Docs**: http://localhost:8090/docs\n\n### 3. Generate Traffic \u0026 Trigger Anomalies\n\n```bash\n# Generate steady load\nmake chaos-load\n\n# Or inject random chaos\nmake chaos\n\n# Or create a traffic spike\nmake chaos-spike\n```\n\n### 4. Watch the Magic Happen\n\n1. Go to the **Dashboard** (http://localhost:3000)\n2. Navigate to **Anomalies** tab - watch real-time detections\n3. Check **Actions** tab - see auto-remediation in action\n4. View **Grafana** for detailed metrics visualization\n\nSee the [Screenshots](#screenshots) section above for visual examples of each interface.\n\n## Detailed Usage\n\n### Makefile Commands\n\n```bash\nmake help          # Show all commands\nmake up            # Start all services\nmake down          # Stop all services\nmake build         # Build Docker images\nmake rebuild       # Rebuild and restart\nmake logs          # View logs\nmake status        # Check service status\nmake health        # Health check all services\nmake chaos         # Inject random chaos\nmake chaos-load    # Generate steady load\nmake chaos-spike   # Generate traffic spike\nmake clean         # Clean everything (including volumes)\nmake test          # Run end-to-end test\nmake urls          # Display all service URLs\n```\n\n### Chaos Simulator CLI\n\n```bash\ncd chaos_simulator\n\n# Install dependencies\npip install -r requirements.txt\n\n# Check health of all services\npython chaos.py health\n\n# Generate load on specific service\npython chaos.py load --service orders --requests 100\n\n# Traffic spike\npython chaos.py spike --service payments --duration 60\n\n# Random chaos for 2 minutes\npython chaos.py chaos --duration 120\n\n# Steady background load for 5 minutes\npython chaos.py steady --duration 300\n```\n\n### Policy Configuration\n\nEdit `policy_engine/policies.yml`:\n\n```yaml\npolicies:\n  - name: \"orders_high_latency_restart\"\n    condition: \"latency \u003e 0.5\"      # Trigger when latency \u003e 500ms\n    action: \"restart_container\"      # Action to execute\n    service: \"orders\"                # Target service\n    cooldown: 300                    # Wait 5 minutes before repeating\n    enabled: true                    # Enable/disable policy\n```\n\nAvailable actions:\n- `restart_container`: Restart the Docker container\n- `scale_up`: Scale service replicas (K8s)\n- `alert`: Send alert notification\n\n### API Examples\n\n**Get Anomalies:**\n```bash\ncurl http://localhost:8080/predict | jq\n```\n\n**Get Services Health:**\n```bash\ncurl http://localhost:8080/services/health | jq\n```\n\n**Get Policy Status:**\n```bash\ncurl http://localhost:8081/status | jq\n```\n\n**Get Remediation Actions:**\n```bash\ncurl http://localhost:8081/actions | jq\n```\n\n**Toggle Auto-Remediation:**\n```bash\ncurl -X POST http://localhost:8081/toggle | jq\n```\n\n## Testing End-to-End Flow\n\n### Scenario 1: High Latency Detection \u0026 Recovery\n\n```bash\n# 1. Start the platform\nmake up\n\n# 2. Generate traffic with latency spikes\nmake chaos-spike\n\n# 3. Watch the dashboard\nopen http://localhost:3000\n\n# Expected outcome:\n# - Anomaly service detects high latency\n# - Policy engine triggers restart action\n# - Service recovers automatically\n# - All actions logged in dashboard\n```\n\n### Scenario 2: High Error Rate\n\n```bash\n# 1. Enable chaos mode (already enabled in docker-compose)\n# 2. Generate high load\ncd chaos_simulator\npython chaos.py load --service payments --requests 200\n\n# 3. Monitor\n# - Check Anomalies tab for error_rate anomalies\n# - Check Actions tab for remediation history\n# - View Grafana for error rate graphs\n```\n\n## Grafana Dashboards\n\nAccess Grafana at http://localhost:3001 (admin/admin)\n\nPre-configured dashboard includes:\n- Service health overview\n- Request latency (p99) per service\n- Error rate trends\n- CPU usage\n- Request rate\n\nTo import additional dashboards:\n1. Click \"+\" → \"Import\"\n2. Upload `monitoring/grafana/dashboards/main-dashboard.json`\n\n## Configuration\n\n### Environment Variables\n\n**Microservices:**\n- `CHAOS_ENABLED`: Enable chaos injection (default: true)\n- `FAILURE_RATE`: Probability of failures (default: 0.1)\n- `LATENCY_SPIKE_RATE`: Probability of latency spikes (default: 0.15)\n\n**Anomaly Service:**\n- `PROMETHEUS_URL`: Prometheus endpoint\n- `CHECK_INTERVAL`: Detection interval in seconds (default: 30)\n\n**Policy Engine:**\n- `AUTO_REMEDIATION_ENABLED`: Enable auto-remediation (default: true)\n- `CHECK_INTERVAL`: Evaluation interval in seconds (default: 30)\n\n### Adjusting Sensitivity\n\nEdit `anomaly_service/main.py`:\n\n```python\ndetector = SimpleAnomalyDetector(\n    window_size=20,      # Number of historical data points\n    sensitivity=2.5      # Standard deviations for threshold\n)\n```\n\nLower sensitivity = more anomalies detected  \nHigher sensitivity = only severe anomalies\n\n### AI Configuration\n\nThe AI service requires a Groq API key to enable LLM-powered features.\n\n**Option 1: Environment Variable (Recommended for Production)**\n```bash\nexport GROQ_API_KEY=\"your-groq-api-key-here\"\ndocker compose up -d\n```\n\n**Option 2: .env File (Local Development)**\n```bash\n# Create .env file in project root\necho \"GROQ_API_KEY=your-groq-api-key-here\" \u003e .env\n\n# Start with env file\ndocker compose --env-file .env up -d\n```\n\n**Option 3: GitHub Secrets (CI/CD)**\n```bash\n# Add secret to GitHub repository\ngh secret set GROQ_API_KEY -b\"your-groq-api-key-here\" -R suhasramanand/predictive-reliability-platform\n\n# Or via GitHub UI:\n# Repository → Settings → Secrets and variables → Actions → New repository secret\n```\n\n**Verify AI Service:**\n```bash\ncurl http://localhost:8090/health\n# Expected: {\"status\":\"healthy\",\"service\":\"ai-service\"}\n\n# Test chat endpoint\ncurl -X POST http://localhost:8090/chat \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"query\":\"What is SRE?\"}'\n```\n\n**Without GROQ_API_KEY:**\n- AI features will be disabled gracefully\n- Dashboard will show \"AI Unavailable\" status\n- All other platform features continue to work normally\n\n**Getting a Groq API Key:**\n1. Visit https://console.groq.com\n2. Sign up for a free account\n3. Navigate to API Keys\n4. Create a new API key\n5. Copy and set as environment variable\n\n## Troubleshooting\n\n### Services won't start\n```bash\n# Check Docker is running\ndocker ps\n\n# Check port conflicts\nlsof -i :3000,8001,8002,8003,8080,8081,9090\n\n# View logs\nmake logs\n```\n\n### Anomalies not detected\n```bash\n# Verify Prometheus is scraping\nopen http://localhost:9090/targets\n\n# Check anomaly service logs\ndocker logs anomaly-service\n\n# Generate more traffic\nmake chaos-load\n```\n\n### Auto-remediation not working\n```bash\n# Check policy engine status\ncurl http://localhost:8081/status | jq\n\n# Verify Docker socket is mounted\ndocker exec policy-engine ls -la /var/run/docker.sock\n\n# Check policies are loaded\ncurl http://localhost:8081/policies | jq\n```\n\n### Dashboard not loading data\n```bash\n# Check service connectivity\ndocker exec dashboard ping anomaly-service\ndocker exec dashboard ping policy-engine\n\n# Check nginx proxy config\ndocker logs dashboard\n```\n\n## Project Structure\n\n```\npredictive-reliability-platform/\n├── services/\n│   ├── orders_service/          # Orders microservice\n│   ├── users_service/           # Users microservice\n│   └── payments_service/        # Payments microservice\n├── anomaly_service/             # Anomaly detection service\n├── policy_engine/               # Auto-remediation engine\n├── chaos_simulator/             # Chaos engineering tool\n├── dashboard/                   # React TypeScript dashboard\n├── monitoring/                  # Observability configs\n│   ├── prometheus.yml\n│   ├── loki-config.yml\n│   └── grafana/\n├── docker-compose.yml           # Orchestration\n├── Makefile                     # Automation commands\n└── README.md                    # This file\n```\n\n## Production Deployment\n\n### AWS EKS (Terraform)\n\n```bash\ncd terraform\nterraform init\nterraform plan\nterraform apply\n\n# Update kubeconfig\naws eks update-kubeconfig --name predictive-reliability-cluster\n\n# Deploy\nkubectl apply -f k8s/\n```\n\n### Key Considerations\n\n1. **Security**: Use secrets management (AWS Secrets Manager, Vault)\n2. **Scaling**: Configure HPA for microservices\n3. **Persistence**: Use RDS for state, EBS for Prometheus\n4. **Monitoring**: Send alerts to PagerDuty/Slack\n5. **Networking**: Configure ALB/NLB for ingress\n6. **Observability**: Consider managed solutions (Amazon Managed Prometheus, Grafana Cloud)\n\n## Learning Outcomes\n\nThis project demonstrates:\n\n- **Microservices Architecture**: Service isolation, API design\n- **Observability**: Metrics, logs, traces (Prometheus, Loki, Jaeger)\n- **SRE Practices**: SLO/SLI monitoring, error budgets, incident response\n- **Machine Learning**: Time-series analysis, anomaly detection\n- **Automation**: Policy-driven remediation, self-healing systems\n- **DevOps**: Docker, Docker Compose, CI/CD concepts\n- **Chaos Engineering**: Failure injection, resilience testing\n- **Full-Stack Development**: React, TypeScript, Python, FastAPI\n\n## Future Enhancements\n\n- [ ] Kubernetes deployment manifests\n- [ ] Terraform modules for AWS/GCP/Azure\n- [ ] Advanced ML models (LSTM, Prophet)\n- [ ] Slack/PagerDuty integration\n- [ ] Custom Grafana dashboards with alerts\n- [ ] Service mesh integration (Istio)\n- [ ] Cost optimization recommendations\n- [ ] Performance profiling\n- [ ] Security scanning and compliance checks\n\n## Contributing\n\nThis is a proof-of-concept project. Feel free to:\n- Fork and extend functionality\n- Add new microservices\n- Improve anomaly detection algorithms\n- Create additional policies\n- Enhance the dashboard\n\n## License\n\nMIT License - Feel free to use this project for learning and demonstration purposes.\n\n## Author\n\nBuilt as a comprehensive SRE/DevOps demonstration project.\n\n## Acknowledgments\n\n- Prometheus Project\n- Grafana Labs\n- Jaeger/OpenTelemetry\n- FastAPI Framework\n- React Community\n\n---\n\n**Ready to see it in action?** Run `make up` and visit http://localhost:3000!\n\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsuhasramanand%2Fpredictive-reliability-platform","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsuhasramanand%2Fpredictive-reliability-platform","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsuhasramanand%2Fpredictive-reliability-platform/lists"}