Every AI tool you need, in one place.

TruLens is an open-source framework for evaluating and tracking LLM applications. Feedback functions assess truthfulness, harmlessness, and helpfulness…

DeepEval is an open-source LLM evaluation framework with 14+ evaluation metrics including hallucination, answer relevancy, and faithfulness. pytest-style…

Portkey is an AI gateway providing unified access to 200+ LLMs with built-in observability, caching, and fallbacks. Production-grade…

Unify automatically routes LLM requests to the cheapest or fastest provider based on your optimization criteria. Benchmark any…

Eden AI provides a unified API for 100+ AI models across text, image, audio, and video. Test and…

Agenta is an open-source LLMOps platform for prompt management, evaluation, and deployment. Teams collaborate on prompts, run systematic…

HoneyHive is an AI evaluation and observability platform for teams building LLM applications. Dataset management, automated evaluations, and…

Mirascope is a Python toolkit for building LLM applications with clean abstractions for prompts, calls, and extractions. Type-safe…

Weaviate is an open-source vector database with built-in ML model integration. Automatically vectorizes data as it's imported and…

Qdrant is a high-performance vector database optimized for production AI applications. Rust-based engine delivers exceptional speed with filtering…