# Changelog

Latest release updates from the Langfuse team. Check out our [Roadmap](/content/docs/roadmap/index.html) to see what's next.

## All posts

[**Manage dashboards via API, CLI, and MCP**  
Create and manage dashboards and widgets programmatically through the public API and Langfuse CLI, let AI agents build them via the Langfuse MCP server, or ask the Langfuse Assistant in the UI.  
4 Days Ago](/content/changelog/2026-07-17-dashboard-and-widget-operations-in-api/index.html)  
[**Start with root observations**  
Projects using app-root-aware Langfuse SDKs now open the observations table with a focused view of outer roots and application entry points.  
6 Days Ago](/content/changelog/2026-07-15-root-observations-default/index.html)  
[**Graph View: Aggregated and Expanded modes**  
The trace graph view now offers two layouts, an aggregated overview and an expanded as-it-ran DAG, on a rebuilt deterministic renderer.  
8 Days Ago](/content/changelog/2026-07-13-graph-view-modes/index.html)  
[**Filter by boolean scores**  
Filter Langfuse tables by true or false score values.  
11 Days Ago](/content/changelog/2026-07-10-boolean-score-filters/index.html)  
[**Evaluate tool calls**  
Access recorded tool calls directly in code and LLM-as-a-Judge evaluators.  
11 Days Ago](/content/changelog/2026-07-10-evaluator-tool-calls/index.html)  
[**Home, now a dashboard you can customize**  
Choose which dashboard shows on Home, reuse Home widgets in your own dashboards, and copy, duplicate, and share widgets as portable JSON.  
11 Days Ago](/content/changelog/2026-07-10-home-is-a-dashboard/index.html)  
[**Route project notifications to Slack or webhooks**  
Send blob export and evaluator deactivation alerts to Slack or a webhook.  
11 Days Ago](/content/changelog/2026-07-10-project-notification-channels/index.html)  
[**Parquet exports to blob storage**  
Scheduled blob storage exports can now be written as Apache Parquet files. Parquet is the default for new integrations and configurable via the public API.  
13 Days Ago](/content/changelog/2026-07-08-parquet-blob-storage-exports/index.html)  
[**Query experiments via API and MCP**  
Fetch experiments and their items programmatically through the new public API endpoints, or let AI agents explore experiment results via the Langfuse MCP server.  
2 Weeks Ago](/content/changelog/2026-07-07-experiments-public-api-and-mcp/index.html)  
[**Preview media in JSON views**  
Inspect Langfuse media references, data URIs, and media URLs as compact preview tags in JSON viewers, table cells, and dataset item editors.  
3 Weeks Ago](/content/changelog/2026-06-30-media-previews-json-views/index.html)  
[**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 Weeks Ago](/content/changelog/2026-06-26-annotation-queue-keyboard-shortcuts/index.html)  
[**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 Weeks Ago](/content/changelog/2026-06-26-ask-ai-filter-search-bar/index.html)  
[**Trace AI SDK 7 with Langfuse**  
Use @langfuse/vercel-ai-sdk 5.9.0 to trace Vercel AI SDK 7 calls in Langfuse.  
4 Weeks Ago](/content/changelog/2026-06-26-vercel-ai-sdk-7/index.html)  
[**Multi-modal datasets**  
Create Langfuse dataset items with images, audio, video, documents, and other attachments for SDK-based multi-modal experiments.  
4 Weeks Ago](/content/changelog/2026-06-23-multi-modal-datasets/index.html)  
[**Filter Search Bar**  
Filter traces and observations by typing. A fast query bar with operators, full-text search, wildcards, and autocomplete.  
June 19, 2026](/content/changelog/2026-06-19-filter-search-bar/index.html)  
[**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.  
June 19, 2026](/content/changelog/2026-06-19-langfuse-assistant-public-beta/index.html)  
[**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.  
June 19, 2026](/content/changelog/2026-06-19-monitors/index.html)  
[**Score from the browser**  
Use @langfuse/browser to send frontend feedback scores with only a public key.  
June 18, 2026](/content/changelog/2026-06-18-browser-score-ingestion/index.html)  
[**Trace AI SDK v7 beta**  
Use the new @langfuse/vercel-ai-sdk beta package to trace Vercel AI SDK v7 beta calls in Langfuse.  
June 18, 2026](/content/changelog/2026-06-18-vercel-ai-sdk-v7-beta/index.html)  
[**Web Callouts**  
Call any HTTP endpoint from your trace, observation, or session views to trigger external workflows from Langfuse.  
June 17, 2026](/content/changelog/2026-06-17-web-callouts/index.html)  
[**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.  
June 16, 2026](/content/changelog/2026-06-16-python-sdk-export-stage-masking/index.html)  
[**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.  
June 15, 2026](/content/changelog/2026-06-15-delete-evaluator-templates/index.html)  
[**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.  
June 10, 2026](/content/changelog/2026-06-10-evaluators-via-mcp/index.html)  
[**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.  
June 10, 2026](/content/changelog/2026-06-10-scores-v3-api/index.html)  
[**Use OpenAI models on Amazon Bedrock**  
Connect Bedrock-hosted OpenAI models to Langfuse LLM Connections with OpenAI Responses API support.  
June 2, 2026](/content/changelog/2026-06-02-openai-on-amazon-bedrock/index.html)  
[Launch Week 5 🚀  
**Langfuse MCP: now with Observations, Metrics, Scores, Comments and more**  
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](/content/changelog/2026-05-29-mcp-update/index.html)  
[Launch Week 5 🚀  
**Code evaluators**  
Run deterministic Python or TypeScript checks on observations and experiments in Langfuse.  
May 28, 2026](/content/changelog/2026-05-28-code-evaluators/index.html)  
[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](/content/changelog/2026-05-27-clickhouse-full-text-search-fast-mode/index.html)  
[Launch Week 5 🚀  
**Langfuse agent skill**  
Your agent's playbook for production-ready LLM apps  
May 26, 2026](/content/changelog/2026-05-26-langfuse-agent-skill/index.html)  
[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](/content/changelog/2026-05-25-experiment-ci-cd-gates/index.html)  
[**Blob storage, PostHog, and Mixpanel exports default to enriched observations for new Cloud projects**  
New Langfuse Cloud projects use enriched observations for blob storage, PostHog, and Mixpanel exports. The legacy traces/observations sources stay available on existing projects and self-hosted deployments.  
May 20, 2026](/content/changelog/2026-05-20-blob-storage-enriched-default/index.html)  
[**Sign in with ClickHouse Cloud**  
Use your ClickHouse Cloud account to sign in to Langfuse Cloud, and link it to an existing Langfuse account.  
May 18, 2026](/content/changelog/2026-05-18-sign-in-with-clickhouse-cloud/index.html)  
[**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. Shrink files and drop fields you don't want to land in your warehouse.  
May 15, 2026](/content/changelog/2026-05-15-blob-storage-export-field-groups/index.html)  
[**Trace context on /api/public/v2/observations**  
Fetch a trace's tags, release, and trace name directly on each observation row  
May 15, 2026](/content/changelog/2026-05-15-v2-observations-trace-context/index.html)  
[**Introducing Langfuse Academy**  
Langfuse Academy is our open explanation of the AI engineering lifecycle: tracing, monitoring, datasets, experiments, and evaluation, and how the pieces fit together.  
May 14, 2026](/content/changelog/2026-05-14-langfuse-academy/index.html)  
[**Self-Service Enterprise SSO Setup**  
Organization admins on Langfuse Cloud can now verify domains and configure Enterprise SSO directly in settings.  
May 8, 2026](/content/changelog/2026-05-08-self-service-enterprise-sso-setup/index.html)  
[**Langfuse Cloud Japan**  
A new dedicated cloud region in Tokyo keeps traces, prompts, and evaluation data inside Japan.  
April 27, 2026](/content/changelog/2026-04-27-langfuse-cloud-japan/index.html)  
[**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](/content/changelog/2026-04-15-llm-as-a-judge-api/index.html)  
[**Amazon Bedrock API Keys**  
Use Amazon Bedrock API keys to connect Bedrock models to Langfuse for Playground, LLM-as-a-judge evaluations, and prompt experiments.  
April 13, 2026](/content/changelog/2026-04-13-amazon-bedrock-api-keys/index.html)  
[**Experiments as a First-Class Concept**  
Experiments now live alongside Datasets as their own top-level feature—run them with or without datasets, compare across runs, and track progress over time.  
April 13, 2026](/content/changelog/2026-04-13-experiments-rebuild/index.html)  
[**Free-Form Text Scores**  
Capture open-ended feedback and qualitative annotations with the new TEXT score type.  
April 10, 2026](/content/changelog/2026-04-10-text-scores/index.html)  
[**Boolean LLM-as-a-Judge Scores**  
LLM-as-a-Judge evaluators can now return boolean scores for `true` / `false` decisions.  
April 8, 2026](/content/changelog/2026-04-08-boolean-llm-as-a-judge-scores/index.html)  
[**Updates to Dashboards**  
Detailed reference for how dashboards behave differently in "Fast Preview" — trace counts, histograms, filters, and more.  
March 23, 2026](/content/changelog/2026-03-23-v4-dashboard-changes/index.html)  
[**Categorical LLM-as-a-Judge Scores**  
LLM-as-a-Judge evaluators can now return categorical scores in addition to numeric ones.  
March 20, 2026](/content/changelog/2026-03-20-categorical-llm-as-a-judge-scores/index.html)  
[**Simplify Langfuse for Scale**  
Langfuse now delivers faster product performance at scale. See the overview page for rollout details, access, and migration steps.  
March 10, 2026](/content/changelog/2026-03-10-simplify-for-scale/index.html)  
[**Langfuse CLI**  
Fully use Langfuse from the CLI. Built for AI agents and power users.  
February 17, 2026](/content/changelog/2026-02-17-langfuse-cli/index.html)  
[**Evaluate Individual Operations: Faster, More Precise LLM-as-a-Judge**  
Observation-level evaluations enable precise operation-specific scoring for production monitoring.  
February 13, 2026](/content/changelog/2026-02-13-observation-level-evals/index.html)  
[**Run Experiments on Versioned Datasets**  
Fetch datasets at specific version timestamps and run experiments on historical dataset versions via UI, API, and SDKs for full reproducibility.  
February 11, 2026](/content/changelog/2026-02-11-versioned-dataset-experiments/index.html)  
[**Corrected Outputs for Traces and Observations**  
Capture improved versions of LLM outputs directly in trace views. Build fine-tuning datasets and drive continuous improvement with domain expert feedback.  
January 14, 2026](/content/changelog/2026-01-14-corrected-outputs/index.html)  
[**Inline Comments on Observation I/O**  
Anchor comments to specific text selections within trace and observation input, output, and metadata fields.  
January 7, 2026](/content/changelog/2026-01-07-inline-comments-on-trace-io/index.html)