Changelog

All posts

Keyboard shortcuts for annotation queues - Process an annotation queue without the mouse: arrow through items, jump between score fields, pick options with number keys, and complete with Cmd+Enter. 4 Days Ago

Ask AI in the Filter Search Bar - Describe the filters you want in plain language and the search bar drafts them as editable query pills. Opt-in on Langfuse Cloud, powered by AWS Bedrock with zero data retention. 4 Days Ago

Trace AI SDK 7 with Langfuse - Use @langfuse/vercel-ai-sdk 5.9.0 to trace Vercel AI SDK 7 calls in Langfuse. 4 Days Ago

Multi-modal datasets - Create Langfuse dataset items with images, audio, video, documents, and other attachments for SDK-based multi-modal experiments. 7 Days Ago

Filter Search Bar - Filter traces and observations by typing. A fast query bar with operators, full-text search, wildcards, and autocomplete. 11 Days Ago

Langfuse Assistant - The Langfuse Assistant is now in public beta for everyone on Langfuse Cloud. Ask questions about your traces, observations, and metrics in plain language. 11 Days Ago

Monitors and Alerts - Create monitors that watch cost, quality, and latency metrics and notify your team over Slack, webhooks, or GitHub Actions when they move outside expected ranges. 11 Days Ago

Score from the browser - Use @langfuse/browser to send frontend feedback scores with only a public key. 12 Days Ago

Trace AI SDK v7 beta - Use the new @langfuse/vercel-ai-sdk beta package to trace Vercel AI SDK v7 beta calls in Langfuse. 12 Days Ago

Web Callouts - Call any HTTP endpoint from your trace, observation, or session views to trigger external workflows from Langfuse. 13 Days Ago

Mask exported spans in Python - Run media detection and configured masking on every span accepted by the Python SDK span processor, including third-party OpenTelemetry spans. 2 Weeks Ago

Delete evaluator templates - Remove evaluator templates you no longer need from the UI, the unstable public API, and MCP, with safeguards that block deletion while rules still depend on them. 2 Weeks Ago

Manage evaluators via MCP - Set up evaluators and evaluation rules from AI agents through the Langfuse MCP server, and create code evaluators through the unstable public API. 3 Weeks Ago

Scores API v3 - Cursor-based pagination, a typed value field, and list-based filters with numeric ranges on the new GET /api/public/v3/scores endpoint. 3 Weeks Ago

Use OpenAI models on Amazon Bedrock - Connect Bedrock-hosted OpenAI models to Langfuse LLM Connections with OpenAI Responses API support. 4 Weeks Ago

Launch Week 5 🚀 Langfuse MCP - The hosted Langfuse MCP server now includes new tools for working with observations, metrics, scores, datasets, comments, and annotation queues from AI agents. May 29, 2026

Launch Week 5 🚀 Code evaluators - Run deterministic Python or TypeScript checks on observations and experiments in Langfuse. May 28, 2026

Launch Week 5 🚀 Full-Text Search - Langfuse Cloud is rolling out ClickHouse full-text search, improving UI search and adding the matches operator to Observations API v2. May 27, 2026

Launch Week 5 🚀 Langfuse agent skill - Your agent's playbook for production-ready LLM apps. May 26, 2026

Launch Week 5 🚀 Experiments CI/CD integration - Run langfuse experiments in GitHub Actions to catch quality regressions before releasing changes to production. May 25, 2026

Blob storage, PostHog, and Mixpanel exports default to enriched observations - New Langfuse Cloud projects use enriched observations for blob storage, PostHog, and Mixpanel exports. May 20, 2026

Sign in with ClickHouse Cloud - Use your ClickHouse Cloud account to sign in to Langfuse Cloud. May 18, 2026

Choose columns and compress blob storage exports - Pick which field groups are written to each row and enable gzip compression in scheduled S3, GCS, and Azure exports. May 15, 2026

Trace context on /api/public/v2/observations - Fetch a trace's tags, release, and trace name directly on each observation row. May 15, 2026

Introducing Langfuse Academy - Langfuse Academy is an open explanation of the AI engineering lifecycle. May 14, 2026

Self-Service Enterprise SSO Setup - Organization admins can now verify domains and configure Enterprise SSO directly in settings. May 8, 2026

Langfuse Cloud Japan - A new dedicated cloud region in Tokyo. April 27, 2026

Manage LLM-as-a-Judge evaluators via the API - Create, version, and update LLM-as-a-Judge evaluators and evaluation rules programmatically through the (unstable) public API. April 15, 2026

Amazon Bedrock API Keys - Use Amazon Bedrock API keys to connect Bedrock models to Langfuse. April 13, 2026

Experiments as a First-Class Concept - Experiments now live alongside Datasets as their own top-level feature. April 13, 2026

Free-Form Text Scores - Capture open-ended feedback and qualitative annotations with the new TEXT score type. April 10, 2026

Boolean LLM-as-a-Judge Scores - LLM-as-a-Judge evaluators can now return boolean scores. April 8, 2026

Updates to Dashboards - Detailed reference for how dashboards behave differently in "Fast Preview". March 23, 2026

Categorical LLM-as-a-Judge Scores - LLM-as-a-Judge evaluators can now return categorical scores. March 20, 2026

Simplify Langfuse for Scale - Langfuse now delivers faster product performance at scale. March 10, 2026

Langfuse CLI - Fully use Langfuse from the CLI. February 17, 2026

Evaluate Individual Operations - Observation-level evaluations enable precise operation-specific scoring for production monitoring. February 13, 2026

Run Experiments on Versioned Datasets - Fetch datasets at specific version timestamps and run experiments on historical dataset versions. February 11, 2026

Corrected Outputs for Traces and Observations - Capture improved versions of LLM outputs directly in trace views. January 14, 2026

Inline Comments on Observation I/O - Anchor comments to specific text selections within trace and observation input, output, and metadata fields. January 7, 2026

Filter Observations by Tool Calls - Add filtering, table columns, and dashboard widgets for analyzing tool usage. December 22, 2025

v2 Metrics and Observations API (Beta) - New high-performance v2 APIs for metrics and observations. December 17, 2025

Dataset Item Versioning - Track dataset changes over time with automatic versioning. December 15, 2025

OpenAI GPT-5.2 support - Langfuse now supports OpenAI GPT-5.2 with day 1 support. December 12, 2025

Batch Add Observations to Datasets - Select multiple observations and add them to datasets with flexible field mapping. December 11, 2025

Pricing Tiers for Accurate Model Cost Tracking - Support for pricing tiers for models with context-dependent pricing. December 2, 2025

Hosted MCP Server for Prompt Management - Native MCP server with write capabilities for AI agents to fetch and update prompts. November 20, 2025

OpenAI GPT-5.1 support - Langfuse now supports OpenAI GPT-5.1 with day 1 support. November 14, 2025

Launch Week 4 🚀 Organize Your Datasets in Folders - Use slashes in dataset names to create folders for better organization. October 27, 2025

Launch Week 4 🚀 JSON Schema Enforcement for Dataset Items - Define JSON schemas for dataset inputs and expected outputs. November 6, 2025