An open-source LLM observability proxy: add one line pointing your existing API calls through it and it logs every prompt and completion, with dashboards for cost, latency and usage per user or feature.
Visit tool This is mine — claim it
Listing URL: https://www.helicone.ai
Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.
<iframe src="https://wingmanprotocol.com/embed/card/helicone" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="Helicone — live on WingMan Protocol"></iframe>
Or the one-line script:
<script src="https://wingmanprotocol.com/embed/card.js" data-slug="helicone" async></script>
Or a README badge:
[](https://wingmanprotocol.com/directory/helicone?utm_source=badge)
A model-deployment platform for running custom or open-source models (including LLMs) in production, handling autoscaling, GPU provisioning and inference optimi
A hosted inference platform for open-source and fine-tuned LLMs, aimed at teams that want fast, low-latency API access to those models without running their own
An open-source SDK and proxy server that exposes over a hundred different LLM providers behind one consistent, OpenAI-style API, handling provider fallbacks, ra
An AI gateway that sits in front of however many LLM providers a team uses: one API routes to any of them, with automatic fallbacks/load balancing, response cac
A prompt management platform: version and test prompts outside of application code, log every LLM request automatically, and compare prompt variants against eac
A long-standing ML experiment-tracking platform - logging runs, metrics and model versions - that has extended into LLM app tracing and evaluation (Weave) along