Skip to content
Agents tracked: 283 Downloads (7d): 261M up 5.8% GitHub stars: 6.2M VS Code installs: 151M Releases (7d): 289 Agent status: 1 with issues Updated Oct 9, 2026

Langfuse by Langfuse

An open-source platform for tracing, evaluating and debugging LLM apps and agents: every model and tool call with its cost and latency, prompt management, datasets and evaluations.

Agent tooling for cost, context and memory New · Added to AgentGid on Oct 8, 2026LLM observability and evaluation platformOpen source · MIT (enterprise features under a separate licence)Free to start
Price
Free (OSS)
free and open source
Popularity
Top 3 in Agent tooling
Gid Score 63 / 100 · #15 of 283 overall
Trend
Steady
usage down 1.9% over 30 days
Development
Actively updated
latest 4.55.0, yesterday
Community
35.5K GitHub stars
8.7M package downloads a week

What Langfuse does

Key facts

MakerLangfuse
TypeLLM observability and evaluation platform
LicenseMIT (enterprise features under a separate licence)
InterfacesWeb app, Python SDK, TypeScript SDK, OpenTelemetry
Works withIntegrates with OpenAI, LangChain, LlamaIndex, LiteLLM, the OpenAI Agents SDK and other frameworks
Main languageTypeScript
Open issues and PRs1,021

Pricing

Free to self-host. Langfuse Cloud has a free Hobby tier, Core at $29 a month, Pro at $199 a month and Enterprise at $2,499 a month; usage beyond the included 100k units costs $8 per 100k.

Source: official pricing page, checked Oct 9, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT (enterprise features under a separate licence))
  • Where you use itWeb app, Python SDK, TypeScript SDK, OpenTelemetry
  • Closest alternativeLiteLLM · all alternatives

Get started with Langfuse

npmnpm install -g langfuse
PyPIpip install langfuse

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Langfuse works with

Agent frameworks and SDKs

Compare Langfuse with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d VS Code installs Stars Latest release Price
8
LiteLLM NewBerriAI
73 23.1M up 1.8% — — 60.4K+60/day 1.104.2yesterday Free (OSS)
14
Firecrawl NewFirecrawl
63 2.7M down 3.5% down 5.6% — 190K+368/day 2.11.03mo ago Free + $16/mo
21
E2B NewE2B
60 3.7M up 2.6% up 13.7% — 14.2K+24/day 2.53.13d ago Free + $150/mo
34
Composio NewComposio
55 1.7M up 8.4% up 33.7% — 30.5K+16/day 0.13.010d ago Free + $29/mo
35
Crawl4AI NewCrawl4AI
55 351K up 5.9% down 6.5% — 85K+61/day 0.9.416d ago Free (OSS)
63
Mem0 NewMem0
47 692K up 4.8% down 29.9% — 66.8K+63/day 3.3.114d ago Free (OSS)

Head to head: Langfuse vs LiteLLM · Langfuse vs Firecrawl · Langfuse vs E2B · Langfuse vs Composio

Langfuse news

All AI agent news

  1. Release GitHub Releases

    Langfuse 4.55.0 released

    feat(docker): create zero vuln base images and add fips mode; feat(topics): rework the summary system prompt and default facets; feat(web): show ClickHouse organization id in org debug information

  2. New on AgentGid AgentGid

    25 agents added to AgentGid

    LiteLLM, Firecrawl, Langfuse, E2B, Composio, Crawl4AI, Mem0, Repomix, CodeGPT, Context7, Phoenix, Headroom and 13 more

  3. Release GitHub Releases

    Langfuse 4.54.0 released

    feat(topics): classify traces into buckets; feat: add external media storage integration; feat(scores): compile experiment-item and prompt-event reads through the query AST

What changed: recent Langfuse releases

Full changelog

4.55.0
  • feat(docker): create zero vuln base images and add fips mode
  • feat(topics): rework the summary system prompt and default facets
  • feat(web): show ClickHouse organization id in org debug information
  • feat(topics): summarize all facets of a trace in one call
  • feat(skills): import skills from local files and ZIPs
  • feat(skills): add rendered file previews with raw source access
4.54.0
  • feat(topics): classify traces into buckets
  • feat: add external media storage integration
  • feat(scores): compile experiment-item and prompt-event reads through the query AST
  • feat(openai): add structured review output and enhance customer response fixtures
  • feat(analytics): track user-visible error toasts
  • feat(sessions): Make session view use trace transcripts
4.53.0
  • feat(ai-gateway): expose resolution context in response headers, spans and logs
  • fix(web): zinc neutral tokens, surface tokens, observation line and fill colours
  • fix(evals): skip Bedrock URL media interpolation
  • fix(web): filled badge variant, score and tag chips built on it
  • fix(web): tab bar labels at 14px with a thinner neutral underline
  • fix(transcript): tolerate reasoning differences in replayed history
4.52.0
  • feat(trace-batch): bound batches by estimated weight and exclude oversized traces
  • feat(web): show the organization usage breakdown on every deployment
  • feat(auth): remember the last enterprise SSO email on the sign-in form
  • fix(llm): drop retired and superseded models from the Vertex AI default list
  • fix(web): unify card surface across sign-in, sign-up and onboarding
  • fix(evals): use schema-compatible model preflight prompt
4.51.0
  • feat(mcp): support decision-model evaluators
  • feat(experiments): annotate directly from comparison grid
  • feat(audit-logs): log actor info for audited actions and deletions
  • feat(web): pin evaluator actions during table scrolling
  • feat(ai-gateway): correlate requests with a gateway request ID
  • feat(skills): unify file and folder uploads
4.50.0
  • feat(web): show error id in tRPC error toast and include it in issue reports
  • feat(evals): add facet type, built-in protection, and rule idle time
  • feat(evals): show seven-day execution health in evaluator status
  • feat(web): show view owner name or email on avatar hover
  • fix(web): show full metadata JSONPath values in the modern session header
  • fix(api): type read-side metadata on traces, observations and scores as objects

Langfuse popularity and usage data

Langfuse was downloaded 8.7M times from npm and PyPI in the week ending Oct 5, 2026, up 11.2% on the week before and down 1.9% over the last 30 days compared with the 30 before. The GitHub repository has 35.5K stars, 1,250 of them added in the last 30 days. The latest stable release is 4.55.0, published Oct 8, 2026; there were 32 stable releases in the past 30 days. It was mentioned in 13 Hacker News posts and comments over the last 30 days.

Downloads per daynpm and PyPI, 7-day average 1.2M/day
GitHub starsrunning total 35.5K
Hacker News mentionsposts and comments, rolling 7-day total 7 this week

Download the raw daily series: langfuse.csv

Gid Score breakdown

Adoption88
Community65
Attention15
Momentum48

Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.

Langfuse FAQ

How much does Langfuse cost?

Free to self-host. Langfuse Cloud has a free Hobby tier, Core at $29 a month, Pro at $199 a month and Enterprise at $2,499 a month; usage beyond the included 100k units costs $8 per 100k.

Is Langfuse open source?

Yes. Langfuse is open source, released under the MIT (enterprise features under a separate licence) license.

How popular is Langfuse?

Langfuse was downloaded 8.7M times from npm and PyPI in the week ending Oct 5, 2026, up 11.2% on the week before and down 1.9% over the last 30 days compared with the 30 before. The GitHub repository has 35.5K stars, 1,250 of them added in the last 30 days. The latest stable release is 4.55.0, published Oct 8, 2026; there were 32 stable releases in the past 30 days.

What is the latest version of Langfuse?

The latest stable release we track is 4.55.0, published on Oct 8, 2026.

What are the alternatives to Langfuse?

The closest alternatives in the same category by Gid Score are LiteLLM, Firecrawl, E2B, Composio.

For the makers of Langfuse badges, corrections

Add a live badge to your README or site:

AgentGid: #3 in Agent tooling Gid Score: 63/100

[![AgentGid: #3 in Agent tooling](https://agentgid.com/badges/langfuse-rank.svg)](https://agentgid.com/agents/langfuse/)
[![Gid Score: 63/100](https://agentgid.com/badges/langfuse-score.svg)](https://agentgid.com/agents/langfuse/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: langfuse. PyPI: langfuse. GitHub: langfuse/langfuse. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, langfuse.com.