Langfuse
Hacker ApprovedThe most recommended of 3 LLM observability platforms
People recommend it for tracing and debugging LLM calls, with OpenTelemetry support and a self-hostable option. The most common caveat is confusing documentation and a hard implementation.
People recommend it for tracing and debugging LLM calls, with OpenTelemetry support and a self-hostable option. The most common caveat is confusing documentation and a hard implementation.
41 people gave an opinion
- recommend it
- 29
- criticize it
- 12
- approval share
- 71%
Recommended in 9 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 29 people recommend itNeeds 10 or more, met.
- 2.4 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong tracing and debugging support
“Langfuse/LangSmith are useful for cost tracking and debugging post-hoc.”
Comment from 10 Mar 2026 in “Ask HN: How are you monitoring AI agents in production?” “Langfuse + custom OTEL spans has been the most practical combo for us”
Comment from 10 Mar 2026 in “Ask HN: How are you monitoring AI agents in production?” “Langfuse is great for debugging technical issues on individual traces”
Comment from 12 May 2026 in “Launch HN: Voker (YC S24) – Analytics for AI Agents” - Comment from 18 Mar 2026 in “Show HN: Agent Trust – Cryptographic identity and reputation for AI agents”
- Comment from 18 Jan 2026 in “ClickHouse Acquires Langfuse”
Works well with OpenTelemetry
“We like Langfuse for observability via OpenTelemetry. Prompt management is too basic for our needs.”
Comment from 18 Jan 2026 in “ClickHouse Acquires Langfuse” “if you want to mix Sentry, Langfuse, Datadog, etc, OTel is still probably the best option”
Comment from 22 Aug 2026 in “OTel Isn't Going Well (and I Made a Spreadsheet About It)” “Langfuse + custom OTEL spans has been the most practical combo for us”
Comment from 10 Mar 2026 in “Ask HN: How are you monitoring AI agents in production?” Well-liked go-to observability tool
“Langfuse has been my favorite LLM observability solution so far.”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” “Langfuse is by far the best of the langs”
Comment from 16 Jan 2026 in “Langfuse Joins ClickHouse” “I love langfuse, it is my goto.”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” Integrates with LiteLLM and frameworks
“Langfuse has ongoing conferences and is still used by many frameworks.”
Comment from 5 May 2026 in “AI Product Graveyard” “it's got nice integration with langfuse for observability”
Comment from 17 Dec 2025 in “Ask HN: What agent frameworks are you using, and how well do they work?” “Eventually I chose litellm+langfuse”
Comment from 17 Jan 2026 in “Cursor's latest "browser experiment" implied success without evidence”
What people warn about
Each mark is one comment
Confusing docs and hard implementation
“I struggled a lot with actually implementing langfuse due to numerous bugs/confusing AI driven documentation”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” “I think the docs are great to read, but implementing was a completely different story for me”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” “maybe clickhouse can finally make sense of the langfuse documentation”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” GDPR concerns after ClickHouse acquisition
“Since clickhouse is headquartered in the US that means the langfuse cloud is no longer GDPR compliant.”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” “Very sad, for all their marketing around EU, GDPR, privacy and so on.”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” “Will be moving away immediately for this reason.”
Comment from 17 Jan 2026 in “ClickHouse Acquires Langfuse” Complex setup and feature-heavy
“Tools like Langfuse exist, but they aren't designed for game loops and require complex observability setups.”
Comment from 22 Jul 2026 in “Show HN: Vifu – A runtime and visual workflow for building AI-native games” “Langfuse is great but tends to be more feature-heavy”
Comment from 5 Mar 2026 in “Show HN: Logmera – Self-hosted LLM observability for AI apps” Stops at tracing, lacks cost rollups
“they tell 'which' agent failed, but my tool (Argus) tells 'why' that agent failed.”
Comment from 14 Sep 2026 in “Ask HN: What are you working on? (September 2026)” “they show traces but don't roll up to "feature X costs $0.12/invocation."”
Comment from 16 Mar 2026 in “Ask HN: How are you estimating API costs before committing to an architecture?”
Other LLM observability platforms people recommend
The two most recommended other LLM observability platforms, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
See all 3 LLM observability platforms, rankedWhat people said
40 of the 44 comments that mention it, newest first. Each links to the original comment.
“The delay in Langfuse only happens if you are ingesting via outdated SDKs/endpoints.”
“Langfuse in general has broder feature set”
“few minute gap before code execution and traces being available to explore is not a problem, then Langfuse is good”
“they tell 'which' agent failed, but my tool (Argus) tells 'why' that agent failed.”
“I wasnt satisfied with what langfuse, langsmith are offering”
“if you want to mix Sentry, Langfuse, Datadog, etc, OTel is still probably the best option”
“That gives us the best of both worlds: startup-speed, ownership, and roadmap control”
“None of them detect repeated contexts in subsequent steps”
“Tools like Langfuse exist, but they aren't designed for game loops and require complex observability setups.”
“Langfuse is great for debugging technical issues on individual traces”
“Langfuse has ongoing conferences and is still used by many frameworks.”
“they're good at tracing but stop at observation”
“they show traces but don't roll up to "feature X costs $0.12/invocation."”
“Langfuse/LangSmith are useful for cost tracking and debugging post-hoc.”
“Langfuse + custom OTEL spans has been the most practical combo for us”
“Langfuse is great but tends to be more feature-heavy”
“If you need a self-hosted setup with tracing, Langfuse should do the trick and cover like 90% of your pain points.”
“probably could be solved partly through langfuse + hooks, if question just in session history”
“This is a reasonable response. It's worth following up on the V4 non-response, but maintainers are busy and things get missed.”
“Langfuse seemed way better at tracing though.”
“We like Langfuse for observability via OpenTelemetry. Prompt management is too basic for our needs.”
“their software was honestly not that great”
“Very sad, for all their marketing around EU, GDPR, privacy and so on.”
“Will be moving away immediately for this reason.”
“It's just logging/tracing for LLMs.”
“they were pretty behind in terms of features”
“Since clickhouse is headquartered in the US that means the langfuse cloud is no longer GDPR compliant.”
“We use it for our internal doc analysis tool. We can easily extract production genrrations, save them to datasets and test edge cases.”
“Langfuse has been my favorite LLM observability solution so far.”
“I love langfuse, it is my goto.”
“Eventually I chose litellm+langfuse”
“I think the docs are great to read, but implementing was a completely different story for me”
“I thought the docs were pretty good just going through them to see what the product was”
“I struggled a lot with actually implementing langfuse due to numerous bugs/confusing AI driven documentation”
“the painful migration to Clickhouse from v2 to v3”
“maybe clickhouse can finally make sense of the langfuse documentation”
“Langfuse is by far the best of the langs”
“The only thing that exceeds that in our whole stack is the Clickhouse shard, which comes with Langfuse”
“it's got nice integration with langfuse for observability”
“I also get some insight into how the agent performs”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.