DocsRoadmap

Langfuse Roadmap

Langfuse is open source and we want to be fully transparent what we’re working on and what’s next. This roadmap is a living document and we’ll update it as we make progress.

Your feedback is highly appreciated. Feel like something is missing? Add new ideas on GitHub or vote on existing ones. Both are a great way to contribute to Langfuse and help us understand what is important to you.

🚀 Released

10 most recent changelog items:

Subscribe to our mailing list to get occasional email updates about new features.

🚧 In progress

  • Tracing
    • Unified agent graphs
    • New JS SDK based on OpenTelemetry (#1291)
  • Evaluation
    • Improvements to core eval views (e.g. compare run view)
    • Annotate dataset experiments

🔮 Planned

  • Agent Observability
    • Unified agent graphs (#2669) (beta for LangGraph (docs))
    • New span types for tool calls (#2624)
    • Agent evaluations: conversation, response, turn, and trajectory levels
  • Evaluation
    • Rule‑based evaluators (regex, structural checks) (#4671, #4484)
    • Trace LLM‑as‑judge evaluations for debugging & cost tracking
    • Evaluation comparison dashboard: correlation, confusion matrix, overlap histogram
    • SDK abstraction for easy experiment setup and UI‑triggered external runners
    • Sessions & observations support for annotation queues (#7551)
    • Session-level and observation-level llm-as-a-judge
  • Datasets
    • Multi‑modal dataset support (#6883)
    • Run comparison view: filterable, sortable dataset runs with annotation support
    • Bulk add traces to datasets (#7691)
    • Dataset folders (#3935)
    • Input/output schema validation
  • Playground
    • Multi‑modal message support (#6017)
    • Dataset experiments in playground
  • Prompt Management
    • Track prompt variables in production tracing (#5242)
    • Prompt experiments with structured outputs and tool/function support (#5958)
    • Exports & imports for prompts (#1696)
  • Data Platform
    • Webhooks for tracing, dataset, and admin events (#1033) in addition to the existing prompt webhooks
    • In-app routing (e.g. add to annotation queue, trigger evals)
    • Metric‑threshold alerts (#3997)
    • Langfuse Cloud usage-based billing alerts

🙏 Feature requests and bug reports

The best way to support Langfuse is to share your feedback, report bugs, and upvote on ideas suggested by others.

Feature requests

Bug reports

Was this page helpful?