Comet's open-source platform for tracing, evaluating and testing LLM applications and agents.
CATEGORY
Routing & Cost Optimization
Manage how AI applications use models and resources. Explore tools for model routing, response reuse, and controlling inference costs.
- products
- 12
- related topic
- 1
Explore products12
12 matching projects
An open-source framework for testing LLM applications, with 50+ metrics for agents, RAG and chatbots that run like unit tests.
An open-source platform to trace, evaluate and debug AI agents, highlighting where an agent failed.
An observability and evaluation platform for AI agents that traces production, runs evals and catches regressions.
Weights & Biases' toolkit for tracing, evaluating and comparing LLM applications; Weights & Biases is part of CoreWeave.
Arize's source-available platform for tracing, evaluating and debugging LLM applications, which you can run yourself.
An open-source tool and platform for red teaming, security testing and evaluating LLM applications; being acquired by OpenAI.
An open-source platform for tracing, evaluating and improving LLM apps and agents, with prompt management; part of ClickHouse since 2026.
A unified interface for many AI models, helping you compare models and prices for your prompts.
An AI gateway and LLM observability platform for routing and monitoring AI applications.
A Python SDK and proxy server for accessing multiple model providers through a common interface.
A production stack for generative AI applications across an organization, including a gateway for model access.