GitHub repo leaderboard by stars, growth rate and activity.

• langfuse

  #1langfuse/langfuse

  🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

  TypeScript34,413 starslast pushed Yesterday
• mlflow

  #2mlflow/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.

  Python27,892 starslast pushed Yesterday
• promptfoo

  #3promptfoo/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.

  TypeScript24,982 starslast pushed 24 hours ago
• Tencent

  #4Tencent/WeKnora

  Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

  Go21,968 starslast pushed Yesterday
• comet-ml

  #5comet-ml/opik

  Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

  Python21,906 starslast pushed Yesterday
• vibrantlabsai

  #6vibrantlabsai/ragas

  Supercharge Your LLM Application Evaluations 🚀

  Python15,693 starslast pushed 7 months ago
• open-compass

  #7open-compass/opencompass

  OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

  Python7,404 starslast pushed 2 days ago
• Helicone

  #8Helicone/helicone

  🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

  TypeScript6,141 starslast pushed 2 weeks ago
• coze-dev

  #9coze-dev/coze-loop

  Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.

  Go5,714 starslast pushed Yesterday
• Marker-Inc-Korea

  #10Marker-Inc-Korea/AutoRAG

  AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.

  TypeScript5,064 starslast pushed 2 days ago

#	Repo	Language	Stars	30-day trend	Last updated
1	langfuse langfuse/langfuse 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23	TypeScript	34,413		last pushed Yesterday
2	mlflow 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.	Python	27,892		last pushed Yesterday
3	promptfoo 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.	TypeScript	24,982		last pushed 24 hours ago
4	Tencent Tencent/WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.	Go	21,968		last pushed Yesterday
5	comet-ml comet-ml/opik Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.	Python	21,906		last pushed Yesterday
6	vibrantlabsai vibrantlabsai/ragas Supercharge Your LLM Application Evaluations 🚀	Python	15,693		last pushed 7 months ago
7	open-compass open-compass/opencompass OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.	Python	7,404		last pushed 2 days ago
8	Helicone Helicone/helicone 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓	TypeScript	6,141		last pushed 2 weeks ago
9	coze-dev coze-dev/coze-loop Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.	Go	5,714		last pushed Yesterday
10	Marker-Inc-Korea Marker-Inc-Korea/AutoRAG AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.	TypeScript	5,064		last pushed 2 days ago

All · 11,474