Technology · Agentic → Observability · Open Core · wiki:deep
Langfuse is an open-source LLM engineering platform for collaboratively developing, monitoring, evaluating, and debugging AI apps. Core bands: tracing (LLM calls, retrieval, agent actions, sessions), prompt management, evaluations (LLM-as-judge, code, feedback, labeling), and datasets/experiments. Self-hostable (ClickHouse-backed) with cloud option; part of ClickHouse as of early 2026 per project README. Open-core research tag.
Default research pick in this cell for agent traces + prompts + evals in one OSS platform. Prefer Phoenix for OpenInference/Arize; Opik for Comet; Helicone for gateway-first; LangSmith for LangChain SaaS; OpenLLMetry for export-only OTEL.
Instrument the app; ingest traces into Langfuse; manage prompts centrally; run datasets/evals and iterate. Self-host or use Langfuse Cloud.
Related: arize-phoenix · comet-optik · helicone · topics/09-self-monitoring
Scroll inside the canvas to pan
Catalog backlinks — what points here (wiki “what links here”).
Claims below are backed by science sources on disk.
Platform role
langfuse/langfuse · MODERATE
“Observability is essential for understanding and debugging LLM applications. Unlike traditional software, LLM applications involve complex, non-deterministic interactions that can be challenging to monitor and debug.”
Docs / features
Langfuse Overview · MODERATE
“Langfuse is an open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications.”
Tracing notes
Tracing capabilities · MODERATE
“Based on OpenTelemetry to increase compatibility and reduce vendor lock-in”
Features and peers linked from the catalog map — not a second product surface.
Primary repo github.com/langfuse/langfuse · Open Core
technologies/langfuse/README.md
9 tags · 53 out · 55 in · 3 artifacts · 0 gaps · 48 corpus docs
company_review · 2
map_edge · 23
tech_features · 1
tech_quote · 7
tech_readme · 1
tech_science_source · 3
tech_section · 11