Also onAcquisitions·Paydays(Pay schedule)
Langfuse 4.76.0 introduces chronological session list views, topic summaries for the public API and MCP, and improved audit logging for read-access events. The release also includes performance optimizations for ingestion and prompt resolution.
Langfuse 4.75.0 increases AI Gateway limits to 10k requests per minute, simplifies Codex setup, and adds analytics for gateway members.
Features - feat(ai-gateway): filter gateway analytics by user and API key - feat(skills): support version automations - feat(rbac): add AI_GATEWAY organization membership role - feat(monitors): add new monitor automation dialog - feat(ai-gateway): add GitHub Copilot CLI and app setup instructions - feat(ai-gateway): invite new gateway team members with the...
Langfuse 4.72.0 introduces AI Gateway analytics, PagerDuty integration for alerts, and improved trace-level evaluation filtering.
Langfuse 4.71.0 introduces AI gateway analytics for tracking model usage, credentials, and errors. It also adds a self-hosted government plan and improves the topics analysis interface.
Langfuse adds unstable read-only Topics endpoints, batch evaluation tools via MCP, and improved AI gateway key management. It also includes various UI and security fixes.
Langfuse 4.69.0 introduces guided AI gateway setup, skill version management for MCP, and improved tracing features for skill loads and execution issues.
Langfuse 4.68.0 adds MCP tool support, new Treemap and Grid views for Topics, and enhanced AI gateway features including per-connection socket logging and custom API key management.
Langfuse released version 4.67.0, simplifying CLI skill installation and import setup, adding name search and gateway key filters for organization API keys, and updating web filtering controls.
Features - feat(topics): non-blocking clustering for large numbers - feat(topics): name topics by what their facet asks about - feat(routes): add recovery option for V4 experience and update sidebar toggle logic - feat(skills): stabilize API and restore MCP access - feat(ai-gateway): add self-hosted "None" ingestion mode - feat(topics): be transparent about...
Features - feat(trace): Move messages tab and reuse session timeline - feat(api-keys): enable project API key permissions by default - feat: rename Langfuse Assistant to Halo - feat(api-keys): show the Admin role as Full access on API keys - feat(topics): show cost of runs - feat(web): page-based pagination for gateway API keys - feat(transcript): implement...
Features - feat(topics): unify manual trace processing and topic generation - feat(ingestion): measure synchronous OTEL work and preparation codepaths - feat: Add status information on integrations screen directly - feat(traces): add dedicated skills tab - feat(observability): gate ECS and container resource detectors behind a flag - feat(ai-gateway): route...
Features - feat(llm): add organization-level connections - feat(billing): record billable units in an append-only ClickHouse ledger - feat(skills): add CLI import instructions - feat(evals): restyle the evaluator gallery with score previews - feat(topics): show facet descriptions in Configure Topics - feat(topics): assign automatic summaries to the serving...
- feat(llm-connections): label TypeSafe adapter as "TypeSafe (System One)" in picker - perf(worker): poll queue metrics once per interval across workers - ci(notifications): stop sending redundant title, branch, and event to Slack - chore(pricing): correct Claude Sonnet 5.5 cache-read price - fix(web): Improve tool response handling in sessions - fix(web)...
Features - feat(web): require Turnstile on password-reset emails - feat(ci): bump dependabot to opus5.5 - feat(otel): extract media before TypeScript parsing - feat(media): add upload pool with concurrency and byte limits - feat(worker): per-project trace idle time in tracing_readiness_settings - feat(topics): configure Topics on the project's own LLM...
Features - feat(ee): refuse FIPS mode with storage options that compute MD5 - feat(worker): add optional startup jitter before queue registration - feat(auth): hash passwords with PBKDF2 in FIPS mode - feat(web): restore optional Cloudflare Turnstile captcha on credential auth - feat(web): carry the typed email over to the password reset form -...
Features - feat(web): design-system CodeSection replaces CodeView - feat(sessions): Add syntax highlighting to session tool previews - feat(billing): send spend alerts for ClickHouse-billed organizations - feat(web): ask new users what they will use Langfuse for - feat(topics): add adaptive map exploration and compact workspace - feat(evals): revamp...
Features - feat(docker): create zero vuln base images and add fips mode - feat(topics): rework the summary system prompt and default facets - feat(web): show ClickHouse organization id in org debug information - feat(topics): summarize all facets of a trace in one call - feat(skills): import skills from local files and ZIPs - feat(skills): add rendered file...
Features - feat(topics): classify traces into buckets - feat: add external media storage integration - feat(scores): compile experiment-item and prompt-event reads through the query AST - feat(openai): add structured review output and enhance customer response fixtures - feat(analytics): track user-visible error toasts - feat(sessions): Make session view...
Features - feat(trace-batch): bound batches by estimated weight and exclude oversized traces - feat(web): show the organization usage breakdown on every deployment - feat(auth): remember the last enterprise SSO email on the sign-in form Fixes - fix(llm): drop retired and superseded models from the Vertex AI default list - fix(web): unify card surface across...
Features - feat(mcp): support decision-model evaluators - feat(experiments): annotate directly from comparison grid - feat(audit-logs): log actor info for audited actions and deletions - feat(web): pin evaluator actions during table scrolling - feat(ai-gateway): correlate requests with a gateway request ID - feat(skills): unify file and folder uploads -...
Features - feat(web): show error id in tRPC error toast and include it in issue reports - feat(evals): add facet type, built-in protection, and rule idle time Fixes / Improvements - feat(evals): show seven-day execution health in evaluator status - feat(web): show view owner name or email on avatar hover - fix(web): show full metadata JSONPath values in the...
Features - feat(web): add org-level ingestion overview tRPC route - feat(evals): track the evaluator onboarding funnel in PostHog - feat(web): Org-level analytics view - feat(web): add feature activation counts to org ingestion overview - feat(web): Improve org-level analytics view - feat(sessions): Add tool filters to session table Fixes / Improvements -...
Features - feat(seeder): add incident-session scenario for the session timeline - feat(skills): track draft changes and fetch file contents by hash Fixes / Improvements - fix(web): reword AI features data notice to "used to train models" - fix(web): prevent metadata badge descenders from clipping - fix(web): collapsed sidebar rows hide their label fully -...
Features - feat(topics): render and measure dedicated trace transcripts - feat(native): prepare JS events and encode batches through NAPI - feat(observability): label experiment query outcomes for SLOs - feat(worker): add the ClickHouse Native write strategy - feat(ai-gateway): set trace environment from langfuse-environment header - feat(ai-gateway)...
Features - feat(experiments): streamline side-by-side comparison - feat(web): Add formatted json to the dataset item - feat(skills): basic skill management - feat(web): add 100-row page size option to tracing tables Fixes - fix(web): header metrics as plain text on trace, observation and session headers - fix(billing): accept string event-bus timestamps on...
Features feat(llm-connections): send extra headers on Vertex AI Gemini requests feat(worker): add isolated OTEL replay integration harness feat(evals): add conversation-signals decision-model gallery template feat(trace-batching): enhance transcript assembly with timing metrics and token estimates feat(ai-gateway): relay Anthropic Messages with usage...
- refactor(web): reroute leftover feature deep imports through index.ts fix(web): trace page panels fill the window width refactor(web): reroute remaining feature deep imports through index.ts feat: trace messages internal preview fix(web): antialiased body text refactor(web): reroute leftover feature deep imports through index.ts fix(web): remove unused...
Features - feat(web): publish event-loop delay for autoscaling - feat(automations): filter prompt events by label - feat(ai-gateway): add phase spans so request traces have no gaps - feat(ai-gateway): record Codex client metadata as agent metadata - feat(auth): authorize every ingestion event through the policy core - feat(otel): simulate worker admission...
Features - feat(api)!: reject legacy reads for new organizations - feat(ci): deploy AI Gateway automatically to staging - feat(api): attribute legacy GET rejections to clients - feat(web): persistent trace summary strip with tags - feat(filters): metadata key presence operators; coerce legacy empty-substring filters - feat(ai-gateway): isolate caller...
Open-source LLM engineering: traces, evals and prompts.
| Release-notes page | Site | Feed |
|---|---|---|
| Changelog langfuse.com | langfuse.com | None |
| Langfuse v3 stable release langfuse.com | langfuse.com | None |
| Langfuse v4 langfuse.com | langfuse.com | None |
Releasesby Glyph