Heliconehelicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
TL;DR · 30-second scan
helicone (TypeScript) — 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
You want zero-instrumentation LLM logging — just swap the base URL.
Analytics · AI & ML
LLM monitoring via a one-line proxy. ~4k stars. Point your OpenAI/Anthropic base URL at Helicone and instantly get logs, cost tracking, caching, rate-limit handling. The proxy approach has a tradeoff — added latency (~50ms) and you're routing prompts through their infra (self-host fixes this). Less opinionated than Langfuse, easier to drop in.
You want zero-instrumentation LLM logging — just swap the base URL.
You need deep evals, prompt management, or you can't accept proxy latency.
Add this badge to your README to show your project is curated on StackPicks. Free, lightweight (180×28 SVG), and gives your visitors a one-click way to see honest take + alternatives.
[](https://stackpicks.dev/repo/helicone-helicone)
<a href="https://stackpicks.dev/repo/helicone-helicone"><img src="https://stackpicks.dev/api/badge/helicone-helicone" alt="Featured on StackPicks" width="180" height="28" /></a>
Are you the maintainer of Helicone/helicone? Add the badge and we'll feature your project in the weekly curator newsletter.