Updated

Braintrust vs Langfuse

Of the 117 makers' products we know the LLM observability & evals of, 35 chose Langfuse (30%) and 6 Braintrust (5%). Among the 33 launched in 2025, Braintrust is in 0% and Langfuse in 45%.

Two sides of the LLM observability & evals decision: hosted eval platform and open-source platform. When each fits, what it costs, who moves from one to the other, and what makers who chose it say.

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

Which fits you

Choose Braintrust if
  • Your main question is whether a prompt or model change made outputs better or worse

Use it whenYour main question is "did this change make outputs better or worse".

Trade-offClosed source, and the paid tier is priced for teams rather than hobby projects.

Choose Langfuse if
  • You want tracing, prompts and evals in one tool you can self-host for free

Use it whenYou want to own your trace data or keep costs flat as volume grows.

Trade-offSelf-hosting means running Postgres, ClickHouse, Redis and object storage alongside it; otherwise it's a usage-based cloud plan.

At a glance

BraintrustLangfuse
Used by6 makers' products · 11 open-source projects35 makers' products · 58 open-source projects
Cost at default usagetraces 100k traces—$29/mo Core
Downloads1.6M/wk+106% vs npm1.7M/wk+57% vs npm
PricingFree tier with monthly usage credits; paid tier with usage overage; custom Enterprise, including self-hosted. · paid from $249/moFree tier (50k units/mo); usage-based paid plans; fully free to self-host under MIT license. · paid from $29/mo
Free tierYesYes
Open sourceNoYes · self-hostable
Incidents, 90 daysfrom its status page8 (7 major)14 (1 major)

Which makers on your framework pick

Makers' products built with each framework that chose either one, for LLM observability & evals.

FrameworkBraintrustLangfuse
Next.js412All 48 Next.js products' picks →

New launches vs older products

A tool that came first has products from every year since, so its total runs ahead. Here is what products launched each year chose, as a share of those that made the LLM observability & evals decision (by the year they launched on Product Hunt).

LaunchedBraintrustLangfuseProducts
20240% 038% 821
20250% 045% 1533

What makers say

Makers on using it for LLM observability & evals, from Product Hunt and Starter Story interviews, each linked to the source. Products with a page of their own and fuller notes first.

On Braintrust

No maker quote about Braintrust for LLM observability & evals yet.

On Langfuse
Marc gave me an in-person onboarding in SF - I found an issue in our LLM provider config just 30 minutes after the onboarding thanks to Langfuse. 10/10 recommendation
stagewise, the makerSep 2026 ↗
Observability for LLM apps and agents Langfuse helps us trace, debug, and improve agent quality across the platform.
Agentplace.io, the makerSep 2026 ↗
We use it to trace every model call in Flowstep, super useful for debugging
Flowstep, the makerSep 2026 ↗
20 more on the Langfuse page →

Loved and watch-outs

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises.

Braintrust
Most loved
  • Setting up datasets and running evals against different models is quick. HNHN 2HN 3
  • A solid eval platform for checking whether prompts produce consistent results. HNHN 2HN 3
Watch-outs
  • Its core dataset-and-pass-rate workflow is simple enough that teams say they could build it themselves. HNHN 2
  • Unlike Promptfoo or Laminar, it is closed source. HN
Langfuse
Most loved
  • Detailed traces show each agent call and the context it pulled, which makes debugging agent behaviour much easier. PHPH 2HN
  • Token usage and cost are tracked across providers alongside quality, in one place. PHPH 2HN
  • Open source and self-hostable, a common default for teams wanting tracing on their own infrastructure. PHHNHN 2HN 3
Watch-outs
  • Prompt management and experiments feel basic next to the tracing core. HNHN 2HN 3
  • Views are retrospective dashboards, so explaining one run's cost or failure still means reading trace trees by hand. HNHN 2HN 3HN 4
  • The ClickHouse acquisition raised GDPR and data-residency concerns for EU users of the cloud version. HNHN 2
On Product Hunt: 5.0★, 49 reviews · mentioned most: LLM observability, open source, detailed tracing

Who uses each

What makers pair each with

Arize PhoenixOpen-source platformOpenTelemetry-based tracing and evals you can start locally in a notebook, then self-host or move to its cloud.vs Langfuse →
HeliconeProxy loggingGetting request logs, costs and latency by changing one base URL, with no SDK instrumentation.vs Braintrust →vs Langfuse →
LangSmithHosted eval platformApps built on LangChain or LangGraph, where tracing works with almost no setup.vs Braintrust →vs Langfuse →

Questions

Braintrust or Langfuse: which do makers choose?

Of the 117 makers' products we know the LLM observability & evals of, 35 chose Langfuse (30%) and 6 Braintrust (5%). Among the 33 launched in 2025, Braintrust is in 0% and Langfuse in 45%. Choose Braintrust if your main question is whether a prompt or model change made outputs better or worse; choose Langfuse if you want tracing, prompts and evals in one tool you can self-host for free.

When should I pick Braintrust over Langfuse?

Pick Braintrust if: Your main question is whether a prompt or model change made outputs better or worse.

When should I pick Langfuse over Braintrust?

Pick Langfuse if: You want tracing, prompts and evals in one tool you can self-host for free.