Helicone

Open-source LLM observability. Self-hostable, OpenTelemetry-native.

Tracing, evals, prompt management, and dataset tooling for LLM apps — self-host on your own infra or use Langfuse Cloud. The open-source default when you want full ownership of your observability stack.

LangChain's hosted observability + eval platform.

Tracing, dataset management, eval orchestration, and prompt playground from the LangChain team. Pairs naturally if LangChain or LangGraph already runs in your stack, but works standalone via SDKs.

AI gateway with observability, guardrails, and governance.

A production AI gateway that gives apps and agents unified access to 1,600+ LLMs across providers behind a single API, with built-in observability, prompt management, guardrails, and governance. Portkey adds routing, caching, fallbacks, cost limits, PII redaction, RBAC, and an MCP gateway. Its core gateway is open-source; run it self-hosted/hybrid or use the managed cloud, which offers a free tier.

Open-source observability and prompt management for LLM apps.

An open-source platform for monitoring, debugging, and improving LLM applications and chatbots. Lunary combines request tracing, cost and user analytics, versioned prompt management with A/B testing, plus human-in-the-loop review and automated scoring. Self-host the Apache-2.0 community edition or use the managed cloud, which starts free with a 10k-events monthly tier.