Langfuse roadmap

Langfuse is open source, and we want to be transparent about where the project is going. This page summarizes the product areas we are currently investing in.

Each quarter, we host a Langfuse town hall to demo new features and discuss what's next. Watch the latest recording below or subscribe to our event calendar for updates on the next one.

🚧 In progress and coming next

New capabilities

• Langfuse Gateway
  • Provide a thin, bring-your-own-key gateway with virtual keys and access controls across Langfuse Cloud and self-hosted deployments.
  • Connect requests directly to Langfuse tracing and cost tracking, with clear visibility into model usage and spend.
• Proactive issue detection
  • Develop Topics to identify recurring user intents, behaviors, and failure patterns across traces at scale.
  • Surface clusters, outliers, and representative examples so teams can find issues without reviewing every trace.
• Agent transcripts
  • Extend a shared transcript representation across traces and sessions to make long-running agent interactions easier to read.
  • Use transcripts as a foundation for Topics and other improvement workflows.
• In-app agent improvements
  • Help users complete workflows such as LLM-as-a-judge calibration with more capable sandbox tools.
• Multi-span and trajectory evaluations
  • Evaluate complete agent interactions using the observations-first data model.
• Skill management
  • Manage and version agent skills, then trace how agents use them.
• Security and authentication improvements
  • Add granular permissions to API keys, including gateway-specific access.
  • Support user-owned and service-account API keys.
  • Add OAuth authentication to the MCP server so it can respect user-level permissions.
• Organization-level dashboards
  • Provide an aggregated view of cost, quality, and other metrics across an organization's projects.
• Custom trace viewers
  • Build and adapt trace viewers with coding agents.

Self-hosting improvements

• Batch more S3 ingestion events to reduce cost.
• Move ingestion work to Rust in stages to reduce latency and cost.
• Extend Hardening for Government with FIPS-compatible deployment support and hardened images.

✅ Recently released

The 10 most recent changelog updates:

• Jev as a judge(Sep 22, 2026)
• Run evaluators on historical observations(Sep 7, 2026)
• Analyze thousands of observations with the Assistant(Sep 3, 2026)
• Create alerts for evaluators(Sep 2, 2026)
• Build multi-message prompts and evaluate multi-modal inputs(Sep 1, 2026)
• Built-in interactive API reference for self-hosted deployments(Sep 1, 2026)
• Responsive Timeline(Aug 28, 2026)
• Restore evaluator versions(Aug 27, 2026)
• Manage evaluators with the stable API(Aug 27, 2026)
• Enable feature previews for your organization(Aug 25, 2026)

Shape the roadmap

Your feedback helps us decide what to prioritize:

• Suggest a feature or improvement, or vote on ideas from other users.
• Report a bug.
• Discuss your use case with the community on Discord.
• Join a community hour to talk with the Langfuse team.

---

---