← Back to home
Comparison · Infra & APIs

Langfuse vs Merge

A side-by-side editorial comparison of Langfuse and Merge — release velocity, themes, recent moves, and the top alternatives to consider.

Langfuse vs Merge: at a glance

FeatureLangfuseMerge
SectorInfra & APIsInfra & APIs
Velocity score0.06.3
Sparks · 30d01
Top themesllm-observability, evaluation, llm-as-a-judge, experimentsunified-api, agent-infrastructure, mcp, llm-routing
Last editorial update8d ago1h ago
Website

What is Langfuse?

Langfuse promotes Experiments out from under Datasets, making evaluation the primary workflow.

Langfuse's recent work is concentrated almost entirely on the evaluation surface. Experiments were rebuilt as a top-level feature that runs with or without a dataset attached, and can be compared across runs over time. The LLM-as-a-Judge evaluator gained categorical scores in late March and boolean true/false scores a week later, filling out the score types beyond plain numerics. Everything else in the window is documentation or scrape artifacts.

Read the full Langfuse trajectory →

What is Merge?

Merge is becoming the governance layer for agent tool access, not just a unified data API.

Merge ships a weekly digest split across three lines: the original unified API (HRIS, ATS, CRM, accounting, file storage, ticketing), Agent Handler for AI agent connectors, and Gateway for LLM routing. The unified-API half reads as a maintenance grind — every week is dominated by SharePoint, SAP SuccessFactors, Workday and Dayforce sync reliability, pagination and mapping fixes. All of July's directional news came from the other two lines, ending with hundreds of generic MCP connectors folded into the Agent Handler catalog and an AI Guardrails surface with PII detection.

Read the full Merge trajectory →

Langfuse vs Merge: editorial side-by-side

L
Langfuse
INFRA · APIS
0.0

Langfuse promotes Experiments out from under Datasets, making evaluation the primary workflow.

◆ Current state

Langfuse's recent work is concentrated almost entirely on the evaluation surface. Experiments were rebuilt as a top-level feature that runs with or without a dataset attached, and can be compared across runs over time. The LLM-as-a-Judge evaluator gained categorical scores in late March and boolean true/false scores a week later, filling out the score types beyond plain numerics. Everything else in the window is documentation or scrape artifacts.

◆ Where it's heading

The direction is evaluation as the product's centre of gravity rather than an appendage to tracing. Decoupling Experiments from Datasets removes the setup cost of running an eval, and the widening score types let judges express verdicts rather than only magnitudes — both point at teams running evals continuously against live traces instead of curated fixtures. Regional expansion shows up in the feed as Langfuse Cloud Japan. Cadence is the open question: nothing has published since April 21, so this arc is described from a three-month-old window.

◆ Prediction

The score-type buildout and the run-comparison view are converging on scheduled or triggered evaluations against production traces, but the feed has been silent long enough that the next move cannot be called with confidence from these entries alone.

M
Merge
INFRA · APIS
6.3

Merge is becoming the governance layer for agent tool access, not just a unified data API.

◆ Current state

Merge ships a weekly digest split across three lines: the original unified API (HRIS, ATS, CRM, accounting, file storage, ticketing), Agent Handler for AI agent connectors, and Gateway for LLM routing. The unified-API half reads as a maintenance grind — every week is dominated by SharePoint, SAP SuccessFactors, Workday and Dayforce sync reliability, pagination and mapping fixes. All of July's directional news came from the other two lines, ending with hundreds of generic MCP connectors folded into the Agent Handler catalog and an AI Guardrails surface with PII detection.

◆ Where it's heading

The unified API is being maintained, not expanded — new objects arrive at a trickle (expense reports in early July) while the bulk of each week goes to sync stability across existing connectors. Attention has moved to sitting between agents and the tools they call: Merge now offers auth, access control, governance and guardrails over connectors it did not build. Gateway is moving the same way, from a routing product to multi-tenant infrastructure customers resell, via Embedded Routing Stack, bring-your-own keys and per-customer complexity classifiers.

◆ Prediction

Expect the guardrails surface to deepen — PII detection and pre-run/post-run rule labels shipped in the same month, and the generic MCP connectors currently arrive without the tool safety hints Merge applied to its own catalog. The likely next step is extending that governance tooling to the imported MCP servers.

Alternatives to Langfuse and Merge

Other Infra & APIs products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either Langfuse or Merge.

See all Langfuse alternatives → · See all Merge alternatives →

Recent activity from Langfuse and Merge

Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.

  1. 12d agoMergeHundreds of generic MCP connectors land in Agent Handler
  2. 19d agoMergeLink setup flow becomes configurable per integration
  3. 26d agoMergeEmbedded Routing Stack gives Gateway per-customer model controls
  4. 1mo agoMergeGPT-5.6, Grok 4.5 join Gateway; new Professional Plan pricing
  5. 1mo agoMergeiTrent and OmniHR connectors; Slackbot gets its own agent identity
  6. 1mo agoMergeExpense reports endpoint, iTrent and OmniHR join HRIS
  7. 3mo agoLangfuseExperiments promoted to a top-level feature
  8. 3mo agoLangfuseBoolean scores for LLM-as-a-Judge evaluators
  9. 4mo agoLangfuseExperiments as a First-Class Concept
  10. 4mo agoLangfuseBoolean LLM-as-a-Judge Scores
  11. 4mo agoLangfuseReference: dashboard behavior under Fast Preview
  12. 4mo agoLangfuseRoadmap threads1.1k

Frequently asked questions

What is the difference between Langfuse and Merge?

They serve adjacent needs but don't currently overlap on shipped themes. Merge is currently shipping more aggressively (velocity 6.3 vs 0.0), with 1 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.

Is Langfuse better than Merge?

Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Merge is currently shipping more aggressively (velocity 6.3 vs 0.0), with 1 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Infra & APIs products to evaluate alongside.

What are the best alternatives to Langfuse?

Top Langfuse alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "Langfuse alternatives" section above for the current picks, or visit /alternatives/langfuse for the full list with editorial commentary on each.

What are the best alternatives to Merge?

Top Merge alternatives in Infra & APIs are ranked by recent ship velocity. Browse the "Merge alternatives" section above for the current picks, or visit /alternatives/merge-dev for the full list with editorial commentary on each.