Observability, evaluation, prompt management and operations for LLM apps in production.
Ranked by total GitHub stars, refreshed every day.
| # | Repo |
|---|---|
| 1 | Active (pushed in the last 90 days)netdata/netdata The fastest path to AI-powered full stack observability, even for lean teams. 81.4KGo |
| 2 | Active (pushed in the last 90 days)apache/airflow Apache Airflow - A platform to programmatically author, schedule, and monitor workflows 47.5KPython |
| 3 | Active (pushed in the last 90 days)ifixai-ai/iFixAi Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds. 46KPython |
| 4 | Active (pushed in the last 90 days)langfuse/langfuse 🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud. 37.5KTypeScript |
| 5 | Active (pushed in the last 90 days)SigNoz/signoz SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents. Get logs, metrics, and traces in one tool with features like APM, distributed tracing, log management, infra monitoring, etc. Combined with SigNoz MCP and a native AI teammate (in SigNoz Cloud) it helps you build more resilient apps. 32.7KTypeScript |
| 6 | Active (pushed in the last 90 days)mlflow/mlflow The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data. 28.8KPython |
| 7 | Active (pushed in the last 90 days)promptfoo/promptfoo Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic. 27.3KTypeScript |
| 8 | Active (pushed in the last 90 days)cilium/cilium eBPF-based Networking, Security, and Observability 25.9KGo |
| 9 | Active (pushed in the last 90 days)apache/skywalking APM, Application Performance Monitoring System 25KJava |
| 10 | Active (pushed in the last 90 days)PrefectHQ/prefect Prefect is a workflow orchestration framework for building resilient data pipelines in Python. 24.2KPython |
| 11 | Active (pushed in the last 90 days)comet-ml/opik Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. 23.4KPython |
| 12 | Active (pushed in the last 90 days)jaegertracing/jaeger CNCF Jaeger, a Distributed Tracing Platform 23.4KGo |
| 13 | Active (pushed in the last 90 days)openobserve/openobserve Open source observability platform for logs, metrics, traces, RUM (web, android, ios), Session replay, pipelines, SLO and LLM observability. A sophisticated, simple and highly performant alternative to Datadog, Splunk, and Elasticsearch with 140x lower storage costs and single binary deployment. 23.1KTypeScript |
| 14 | Active (pushed in the last 90 days)pranshuparmar/witr Why is this running? Trace any process, port, container, or file back to what started it - CLI + TUI. 23KGo |
| 15 | Active (pushed in the last 90 days)vectordotdev/vector A high-performance observability data pipeline. 22.9KRust |
| 16 | Inactive (no push for over a year, or archived)jina-ai/serve ☁️ Build multimodal AI applications with cloud-native stack 21.9KPython |
| 17 | |
| 18 | |
| 19 | Slowing down (last push 3–12 months ago)Avaiga/taipy Turns Data and AI algorithms into production-ready web applications in no time. 19.5KPython |
| 20 | Active (pushed in the last 90 days)VictoriaMetrics/VictoriaMetrics VictoriaMetrics: fast, cost-effective monitoring solution and time series database 18.1KGo |