An open platform that shows every model call: traces, cost, quality scores and prompt versions. Use it in the cloud or self-host it.
All repositories
Evals & observabilityHelicone
helicone
A gateway and observability platform: change the API address in your code and all model requests get logged, costed and compared. Can be self-hosted.
Who it is for
For those who want LLM logs and cost tracking with almost no code changes.
How to start
- Get an API key at helicone.ai and add credits.
- In your client, change
baseURLtohttps://ai-gateway.helicone.aiand use your Helicone key. - Open the dashboard and look at the request logs.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+71Sep 7 — Oct 6
Author's description
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
More in «Evals & observability»
A long-standing ML platform that now covers LLM apps too: tracing, evaluation, a prompt registry and a model gateway. Plugs into most frameworks.
A command-line tool for testing prompts and agents: describe cases in a config and compare models. Also does red teaming and vulnerability scanning. Plugs into CI.
A platform for debugging and evaluating LLM apps: traces, automated quality checks and dashboards. Supports RAG and agent chains, and can be self-hosted.
OpenAI's framework for evaluating models plus a registry of ready-made benchmarks. A historically important project that shows how eval templates are structured.
A pytest-style framework for testing LLM apps: ready-made metrics for RAG, agents and chatbots, plus trace-based checks. Results can be pushed to a cloud.