Helicone
Open-source LLM observability platform and gateway that logs requests, tokens and costs.
0 members list Helicone, unchanged over the last 12 weeks, data as of 19 October 2026
Members who list Helicone in their Stack, by week.
Be the first to add Helicone
Nobody on Stackness runs Helicone yet. Add it to your stack and you're the first member running it.
About Helicone
Helicone is an open-source platform for observing and managing large language model applications. It functions as both an observability tool and an API gateway, allowing developers to monitor requests, track token usage, and understand costs associated with LLM calls. The platform integrates with various LLM providers including OpenAI, Anthropic, and Azure, as well as frameworks like LangChain and LlamaIndex. Developers can use it to debug applications, analyze performance, and manage prompts through a unified interface.
Helicone is developed by Helicone and distributed under the Apache 2.0 license. The platform is written in TypeScript and offers a free tier with a seven-day trial requiring no credit card to get started. It includes features for monitoring rate limits, setting up alerts, and evaluating model performance, making it suitable for teams building production AI applications.
Checked 19 October 2026.
Nobody on Stackness runs Helicone yet.
Sign up and add itPosts about Helicone
- Run your own LLM proxy to track token usage: LiteLLM in front of Claude Code and Codex
A local LiteLLM proxy logs one row per agent request with tokens, cost, key and session. Setup in about 15 minutes, tested on LiteLLM 1.106.0, October 2026.