Updated

LangSmith vs Ragas

Of the 117 makers' products we know the LLM observability & evals of, 11 chose LangSmith (9%) and 0 Ragas (0%). Among the 33 launched in 2025, LangSmith is in 18% and Ragas in 0%.

Two sides of the LLM observability & evals decision: hosted eval platform and eval and test CLI. 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 LangSmith if
  • Your app is built on LangChain or LangGraph

Use it whenYou already use the LangChain stack.

Trade-offPaid per seat beyond the free tier; self-hosting is enterprise-only.

Choose Ragas if
  • Scoring RAG pipelines — how faithful answers are to the retrieved context and how relevant that context is — and generating test questions from your documents.

Use it whenYour product answers from your own documents and you need numbers to compare chunking, retrieval or prompt changes.

Trade-offA Python library, not a platform — no tracing of live traffic or UI, and LLM-judged metrics cost tokens per run.

At a glance

LangSmithRagas
Used by11 makers' products · 62 open-source projectsNo maker's product yet · 14 open-source projects
Cost at default usagetraces 100k traces$475/mo Developer—
Downloads6.2M/wk−8% vs npm239k/wk
PricingFree tier with a monthly trace limit; paid per-seat plan with usage overage; custom Enterprise, including self-hosted. · paid from $39/seat/moFree (open source).
Free tierYesYes
Open sourceNoYes · self-hostable
Incidents, 90 daysfrom its status page0no public status feed

Which makers on your framework pick

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

FrameworkLangSmithRagas
Next.js40All 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).

LaunchedLangSmithRagasProducts
202419% 40% 021
202518% 60% 033

Cost as you grow

Both cost $0 up to 1k traces; from 10k traces Ragas costs less ($0 vs $25); and still does at 10M traces ($0 vs $49,975). They're different kinds of tool — hosted eval platform and eval and test CLI — so the prices don't buy the same thing.

$0$1,000$5,000$20,0001k10k50k100k500k1M5M10M
RagasLangSmithx: traces per month (trace) · cheapest usable plan at each point, list prices · try your own numbers
The numbers, plan by plan
Traces per monthLangSmithRagas
1,000$0 Developer$0 Self-hosted (open source)
10,000$25 Developer$0 Self-hosted (open source)
50,000$225 Developer$0 Self-hosted (open source)
100,000$475 Developer$0 Self-hosted (open source)
500,000$2,475 Developer$0 Self-hosted (open source)
1,000,000$4,975 Developer$0 Self-hosted (open source)
5,000,000$24,975 Developer$0 Self-hosted (open source)
10,000,000$49,975 Developer$0 Self-hosted (open source)

From each vendor's pricing page: LangSmith, Ragas.

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 LangSmith
LangSmith’s real-time analytics and versioning keep our AI agents rock-solid -- so everything just works better.
Watchman AI, the makerSep 2026 ↗
You can't build AI agents without monitoring. Metadata filtering is strong.
DryMerge, the makerSep 2026 ↗
I deployed the manage Pig agent on LangGraph and it's been smooth sailing!
Pig, the makerSep 2026 ↗
5 more on the LangSmith page →
On Ragas

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

Loved and watch-outs

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

LangSmith
Most loved
  • Tracing through the whole prompt path replaces guesswork when diagnosing agent issues. PH
  • Traces, datasets, annotation queues and evals live in one platform widely used by enterprises. PHHN
  • Pairs tightly with LangChain and LangGraph for debugging stateful agent workflows. PHHNHN 2
Watch-outs
  • It keeps pulling users toward the LangChain platform, and LangChain docs push LangSmith, which feels like lock-in. HNHN 2HN 3HN 4
  • Traces show which agent failed but not why, so root-cause analysis stays manual. HNHN 2HN 3HN 4
  • Viewing your own traces requires a cloud account, with no local-first option. HNHN 2
On Product Hunt: 4.8★, 19 reviews · mentioned most: monitoring AI model performance, chain sequence debugging, evals
RagasNothing that recurs in what we collected yet.

Who uses each

Ragas0 makers' products
None tracked yet; 14 open-source projects declare it.

What makers pair each with

With Ragas
LangfuseOpen-source platformTracing, prompt management and evals in one tool you can run on your own server for free.vs LangSmith →
Arize PhoenixOpen-source platformOpenTelemetry-based tracing and evals you can start locally in a notebook, then self-host or move to its cloud.vs LangSmith →
HeliconeProxy loggingGetting request logs, costs and latency by changing one base URL, with no SDK instrumentation.vs LangSmith →
BraintrustHosted eval platformEval-driven work — scoring outputs and comparing prompts and models side by side in experiments.vs LangSmith →

Questions

LangSmith or Ragas: which do makers choose?

Of the 117 makers' products we know the LLM observability & evals of, 11 chose LangSmith (9%) and 0 Ragas (0%). Among the 33 launched in 2025, LangSmith is in 18% and Ragas in 0%. Choose LangSmith if your app is built on LangChain or LangGraph; choose Ragas if scoring RAG pipelines — how faithful answers are to the retrieved context and how relevant that context is — and generating test questions from your documents.

When should I pick LangSmith over Ragas?

Pick LangSmith if: Your app is built on LangChain or LangGraph.

How do LangSmith and Ragas compare in cost as you grow?

Both cost $0 up to 1k traces; from 10k traces Ragas costs less ($0 vs $25); and still does at 10M traces ($0 vs $49,975). Cheapest usable plan at each scale, at list prices.