All AI tools

Eval, monitor, and improve AI products end-to-end.

LangChain's eval + observability platform.

The ML experiment tracker, now with LLM eval features.

Open-source LLM observability — one-line proxy install.

Enterprise observability and evaluation platform for LLM agents and generative AI applications.

Continuous AI red teaming platform that stress-tests LLM agents for vulnerabilities before they hit production.

Open-source data quality framework for validating the datasets that feed your ML and analytics pipelines.

Prompt management + evals for collaborative AI teams.

Contamination-free LLM benchmark that refreshes its questions monthly to keep frontier models honest.

Collaborative LLM evaluation and observability platform for teams shipping AI features to production.

Open benchmark from UC Berkeley that ranks LLMs on real-world tool-use and function-calling accuracy.

OpenTelemetry-native observability and evaluation platform for LLM agents in production.

Open-source platform for tracking, evaluating, and deploying ML models and LLM applications.

OpenAI's open-source framework for benchmarking LLMs against a shared registry of evaluations.

Open-source evaluation and tracing framework for LLM apps and agents, built on OpenTelemetry.

Production observability, tracing, and evaluation for LLM and agent systems from the Weights & Biases stack.

Live leaderboard and side-by-side comparison hub for 300+ frontier LLMs across reasoning, coding, and multimodal benchmarks.

Lightweight prompt logging + management for OpenAI/Claude apps.

Automated LLM evaluation for hallucinations, safety, and quality.

Open-source LLM observability, prompt management, and evaluation in one platform.

Holistic benchmark suite for evaluating mathematical reasoning in large language models.

Open-source LLM observability and evaluation platform for debugging and monitoring AI agents in production.

Open-source LLM evaluation framework from the UK AI Security Institute with 200+ built-in benchmarks.

Open-source workbench for building, evaluating, and fine-tuning AI agents across 190+ models.