Awesome Opensource Ai

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

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.

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.

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

The LLM Evaluation Framework

AI Observability & Evaluation

the LLM vulnerability scanner

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

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

🐢 Open-Source Evaluation & Testing library for LLM Agents

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

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Evaluation and Tracking for LLM Experiments and AI Agents

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.