Langfuse

Over 100 integrations with agent frameworks, model providers and gateways send traces into Langfuse, data exports to PostHog, Mixpanel and blob storage, and prompt changes notify through webhooks and Slack. These move telemetry in and data out; no connectors that let an agent take authenticated actions in outside systems are documented.

SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21

For agents that run elsewhere, Langfuse provides tracing, evaluation and prompt management, and prompt composability links prompts together. No workflows that sequence, branch or retry an agent's steps, or mix deterministic nodes with agent steps, are documented.

SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21

Langfuse stores traces, prompts and evaluation datasets, and no retrieval structure over the customer's documents or knowledge that grounds an agent's answers is documented; it evaluates the grounding of RAG systems built elsewhere rather than providing one.

SourceLangfuse, langfuse.com pricing and llms.txtread 2026-09-21

Protected deployment labels restrict who can promote a prompt version to production, and CI checks can require an approved baseline before a change ships, so changes to an agent's behavior pass a human-controlled release gate at the policy layer. No approval step, escalation rule or pause before an agent acts at run time is documented.

SourceLangfuse, langfuse.com pricing and llms.txtread 2026-09-21

Reports for Langfuse's SOC 2 Type II and ISO 27001 attestations are available from the Pro plan, and there is a HIPAA-ready region and a GDPR DPA. Access control covers organization- and project-level RBAC, sign-in with Google, Azure AD or GitHub, Enterprise SSO with Okta or Entra ID and SSO enforcement on the Teams add-on, SCIM provisioning, audit logs, client-side data masking and data retention management.

SourceLangfuse, langfuse.com pricing and homepageread 2026-09-21

Hierarchical traces capture every LLM call, tool invocation and retrieval step of an agent run, shown as trace trees and agent graphs with session and user tracking, token cost and latency, and filterable by user, session, cost, latency or metadata; audit logs are separate on Enterprise, data can be exported by batch or scheduled to blob storage and to PostHog or Mixpanel, and historical data access runs 30 days on Hobby, 90 days on Core and 3 years on Pro. That gives run level visibility of steps and tool calls.

SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21

Sessions, users and traces are recorded for inspection, and no session, conversation or long-term memory that an agent reads back as context is documented.

SourceLangfuse, langfuse.com pricing and homepageread 2026-09-21

Langfuse Cloud offers a choice of US, EU or JP data regions, a HIPAA-ready region and AWS PrivateLink, and the MIT-licensed platform self-hosts with Docker Compose, Kubernetes via Helm, or Terraform on AWS, GCP and Azure, with paid Enterprise additions for self-hosted deployments.

SourceLangfuse, langfuse.com pricing, homepage and llms.txtread 2026-09-21

The in-app Langfuse Assistant is the one ready-made agent shipped, and a Langfuse skill packages best-practice workflows for instrumentation, prompt management and API access into a customer's coding agent. Beyond those two, there is no set of prebuilt agents or templates for a buyer to select from.

SourceLangfuse, langfuse.com llms.txt and pricingread 2026-09-21

Online evaluation runs LLM-as-a-judge and code evaluators on production observations as they arrive, and monitors and alerts fire on metric and evaluator thresholds, so Langfuse's evaluation work starts from incoming telemetry with no person initiating each run; prompt changes also emit webhooks.

SourceLangfuse, langfuse.com homepage and pricingread 2026-09-21

Customers configure their own LLM connections, which the Playground uses to test prompts on real production inputs and compare models side by side, and which power the LLM-as-a-judge evaluators the customer sets up. The customer brings its own providers and chooses the models Langfuse's own LLM features run on.

SourceLangfuse, langfuse.com homepage, pricing and llms.txt (LLM Connections)read 2026-09-21

Langfuse documents an extensive public API with published rate limits by plan, native Python and TypeScript SDKs, OpenTelemetry ingestion for Java, Go and other languages, a CLI, a platform MCP server that lets IDE agents manage prompts and query traces, stable ID-based APIs for managing evaluators, and an agent skill.

SourceLangfuse, langfuse.com homepage, pricing and llms.txtread 2026-09-21

Evaluation of the customer's application runs online and offline, covering datasets, experiments from the SDK or UI compared side by side against baselines, LLM-as-a-judge and code evaluators managed by API, custom scores, user feedback and human annotation queues, alerts on evaluator results, and CI checks that block regressions against thresholds and approved baselines. That tests the customer's agent with datasets before production and scores output quality over time.

SourceLangfuse, langfuse.com llms.txt, homepage and pricingread 2026-09-21

Langfuse observes and evaluates agents, and no browser, desktop or computer control by an agent is documented.

SourceLangfuse, langfuse.com homepageread 2026-09-21