Among 23 makers' products we track that are built with Next.js, here's what they chose for LLM observability & evals — each counted from a live-product source.
Open-source platform you can self-host, or a hosted eval product. Open-source tools keep traces on your own servers and cost nothing to run yourself, but you maintain them. Hosted eval platforms give you polished experiment and scoring workflows for a monthly bill, with your data in their cloud.
Langfuse11
Helicone4
LangSmith4
Braintrust4Counts are live products with a source, not market share; a product using two options counts in both.
LangfuseOpen-source platformBest forTracing, prompt management and evals in one tool you can run on your own server for free.
Trade-offSelf-hosting means running Postgres, ClickHouse, Redis and object storage alongside it; otherwise it's a usage-based cloud plan.
11 of the 23 Next.js products here · free tier · open source
HeliconeProxy loggingBest forGetting request logs, costs and latency by changing one base URL, with no SDK instrumentation.
Trade-offProxy logging sees individual requests well but agent steps and eval workflows less deeply; acquired by Mintlify in March 2026, so check its roadmap before building on it.
4 of the 23 Next.js products here · free tier · open source
LangSmithHosted eval platformBest forApps built on LangChain or LangGraph, where tracing works with almost no setup.
Trade-offPaid per seat beyond the free tier; self-hosting is enterprise-only.
4 of the 23 Next.js products here · free tier
BraintrustHosted eval platformBest forEval-driven work — scoring outputs and comparing prompts and models side by side in experiments.
Trade-offClosed source, and the paid tier is priced for teams rather than hobby projects.
4 of the 23 Next.js products here · free tier
Also real options for LLM observability & evals, not seen among these Next.js products yet: Arize Phoenix.