Change Detection - Diff - Changelog

Try our Chrome extension

Easily add the current web-page from your browser directly into your changedetection.io tool, more great features coming soon!

Changedetection.io needs your support!

You can help us by supporting changedetection.io on these platforms;

The more popular changedetection.io is, the more time we can dedicate to adding amazing features!

Many thanks :)

changedetection.io team

Jump

Text
Screenshot
Extract Data

Not yet seconds ago

            False

Not yet seconds ago

Current error-ing screenshot from most recent request

34 minutes ago

Hiring in Berlin and SF Looking for GOATS! ProductResourcesDocsSelf HostingGuidesIntegrationsFAQHandbookChangelogPricingLibrarySecurity & Compliance 19K Get Demo App Sign Up Light Changelog Latest release updates from the Langfuse team. Check out our Roadmap to see what's next. Get updates December 12, 2025 December 12, 2025 OpenAI GPT-5.2 support Langfuse now supports OpenAI GPT-5.2 with day 1 support across all major features. December 11, 2025 December 11, 2025 Batch Add Observations to Datasets Select multiple observations from the observations table and add them to a new or existing dataset with flexible field mapping. December 2, 2025 December 2, 2025 Pricing Tiers for Accurate Model Cost Tracking Langfuse now supports pricing tiers for models with context-dependent pricing, enabling accurate cost calculation for models with context-dependent pricing. November 20, 2025 November 20, 2025 Hosted MCP Server for Langfuse Prompt Management Langfuse now includes a native Model Context Protocol (MCP) server with write capabilities, enabling AI agents to fetch and update prompts directly. November 14, 2025 November 14, 2025 OpenAI GPT-5.1 support Langfuse now supports OpenAI GPT-5.1 with day 1 support for the LLM playground, LLM-as-a-judge evaluations, and comprehensive cost tracking. November 8, 2025 Launch Week 4 🚀 November 8, 2025 Launch Week 4 🚀 Organize Your Datasets in Folders Use slashes in dataset names to create folders for better organization. November 8, 2025 Launch Week 4 🚀 November 8, 2025 Launch Week 4 🚀 JSON Schema Enforcement for Dataset Items Define JSON schemas for your dataset inputs and expected outputs to ensure data quality and consistency across your test datasets. November 7, 2025 Launch Week 4 🚀 November 7, 2025 Launch Week 4 🚀 Score Analytics with Multi-Score Comparison Validate evaluation reliability and uncover insights with comprehensive score analysis. Compare different evaluation methods, track trends over time, and measure agreement between human annotators and LLM judges. November 6, 2025 November 6, 2025 Annotation Support in Experiment Compare View Add human annotations while reviewing experiment results side-by-side. Review experiment outputs, assign scores, and leave comments while viewing full experiment context. November 6, 2025 Launch Week 4 🚀 November 6, 2025 Launch Week 4 🚀 Baseline Support in Experiment Compare View Compare experiment runs side-by-side with baseline designation to systematically identify regressions and improvements November 6, 2025 Launch Week 4 🚀 November 6, 2025 Launch Week 4 🚀 Filters in Compare View Filter experiment results in the compare view to focus on specific subsets, such as items where evaluator scores dropped below a threshold November 5, 2025 Launch Week 4 🚀 November 5, 2025 Launch Week 4 🚀 Langfuse for Agents Trace agents with beautifully rendered tool calls and understand their performance through Agent Evals. November 4, 2025 Launch Week 4 🚀 November 4, 2025 Launch Week 4 🚀 Amazon Bedrock AgentCore Integration Trace AI agents built with Amazon Bedrock AgentCore via OpenTelemetry and Langfuse November 4, 2025 Launch Week 4 🚀 November 4, 2025 Launch Week 4 🚀 @Mentions and Reactions in Comments Tag teammates with @mentions to notify them instantly, and add emoji reactions to comments for quick acknowledgments. November 4, 2025 Launch Week 4 🚀 November 4, 2025 Launch Week 4 🚀 IdP-Initiated SSO Support Langfuse now supports IdP-initiated SSO, allowing users to start authentication directly from their identity provider (e.g., Okta, Azure AD, Keycloak, JumpCloud) November 4, 2025 Launch Week 4 🚀 November 4, 2025 Launch Week 4 🚀 Mixpanel integration We teamed up with Mixpanel to integrate LLM-related product metrics into your existing Mixpanel dashboards. November 3, 2025 Launch Week 4 🚀 November 3, 2025 Launch Week 4 🚀 Advanced Filtering for Public Traces and Observations API The traces endpoint in public API now supports complex JSON-based filtering. November 3, 2025 Launch Week 4 🚀 November 3, 2025 Launch Week 4 🚀 Filter Sidebar for Tables Quickly filter tables by column values in the filter sidebar with one click. October 26, 2025 October 26, 2025 Langchain v1 Support Langfuse SDKs now support Langchain v1 for both Python and JS/TS. The integration remains stable and backward compatible. October 16, 2025 October 16, 2025 LLM-as-a-Judge Execution Tracing & Enhanced Observability Every LLM-as-a-Judge evaluator execution now creates a trace, allowing you to inspect the exact prompts, responses, and token usage for each evaluation. October 10, 2025 October 10, 2025 Spend Alerts Monitor your organization's cloud spending and receive notifications when costs exceed predefined monetary thresholds. September 30, 2025 September 30, 2025 Natural Language Filtering for Traces Filter your traces using plain English queries. Powered by AWS Bedrock with zero data retention. September 30, 2025 September 30, 2025 Structured Output Support for Prompt Experiments Enforce JSON schema response formats in prompt experiments to ensure consistent, parseable outputs for evaluation and analysis. September 29, 2025 September 29, 2025 Mutable Score Configs Score configurations can now be updated after creation. Modify existing configs via API/SDK and UI while keeping all your data safe. September 17, 2025 September 17, 2025 Experiment Runner SDK New high-level SDK abstraction for running experiments on datasets with automatic tracing, concurrent execution, and flexible evaluation. August 28, 2025 August 28, 2025 TypeScript SDK v4 (GA) The new OpenTelemetry-based TypeScript SDK v4 is now generally available with improved DX, modular packages, and seamless integrations. August 27, 2025 August 27, 2025 Additional Observation Types for More Meaningful Span Context New observation types including Agent, Tool, Chain, Retriever, Evaluator, Embedding, and Guardrail provide semantic meaning to your traces. August 26, 2025 August 26, 2025 New End-to-End Walkthrough Videos We've released new comprehensive walkthrough videos covering observability, prompt management, and evaluation to help you get up to speed quickly with Langfuse. August 25, 2025 August 25, 2025 Full-Text Search Across Dataset Items Find dataset items by searching through their actual content with our new full-text search capability August 14, 2025 August 14, 2025 Additional provider options in LLM calls in playground and evals Set additional provider options in your LLM calls in playground and in llm-as-a-judge evaluations. August 7, 2025 August 7, 2025 Docs now available as Markdown (.md) endpoints Append .md to any docs URL to fetch the page as Markdown. Built at compile time for fast, reliable access. August 7, 2025 August 7, 2025 OpenAI GPT-5 pricing now available in Langfuse Day 1 support for OpenAI GPT-5 including tracking token counts and USD spend. August 6, 2025 August 6, 2025 Annotation Queue Assignments Assign users to annotation queues to make it easier for team members to focus on relevant tasks. July 30, 2025 July 30, 2025 Slack Integration for Prompt Webhooks Receive prompt change notifications directly in your Slack channels with our native integration. July 28, 2025 July 28, 2025 LLM Playground with Side-by-Side Comparison The LLM Playground now supports side-by-side prompt comparison with parallel LLM execution. July 28, 2025 July 28, 2025 Sessions in Annotation Queues Annotation Queues now support session-level annotation, making it easier to evaluate multi-turn interactions in your LLM applications. July 25, 2025 July 25, 2025 LiveKit Agents Tracing Integration Trace real-time voice AI agents and multimodal conversations built with LiveKit Agents via OpenTelemetry and Langfuse July 24, 2025 July 24, 2025 Trigger Remote Custom Evaluations from the Langfuse UI Enable non-technical users to trigger external experiment pipelines directly from the Langfuse UI on datasets. July 22, 2025 July 22, 2025 Full-Text Search Across Prompt Content Find prompts by searching through their actual content with our new full-text search capability July 18, 2025 July 18, 2025 AWS SDK Default Credential Provider Chain Support Self-hosted deployments can now use the AWS SDK default credential provider chain for Amazon Bedrock LLM connections. July 11, 2025 July 11, 2025 Webhooks for Prompt Changes Get real-time notifications for new prompt versions, changes to deployment labels or tags, and other edits. July 6, 2025 July 6, 2025 n8n Node for Langfuse Prompt Management Use Langfuse's prompt management capabilities directly in your n8n workflows to build powerful no-code agents. July 3, 2025 July 3, 2025 Gemini 2.5 Pro, Flash, and Flash Lite support for playground, evaluations, and cost tracking Langfuse says hello to Gemini 2.5 Pro (GA), Gemini 2.5 Flash (GA), and Gemini 2.5 Flash Lite (Preview). Support added for the LLM playground, evaluations, and cost tracking. July 2, 2025 July 2, 2025 Message Placeholders in Chat Prompts Inject context or message history into your chat prompts at just the right spot. July 1, 2025 July 1, 2025 Pivot Tables in Custom Dashboards Analyze multi-dimensional data with the new pivot table widget in Langfuse custom dashboards. July 1, 2025 July 1, 2025 Search to Navigate Large Prompt Collections Now it is easier to find prompts in prompt management via the new search bar June 30, 2025 June 30, 2025 Histogram Charts in Custom Dashboards Visualize data distributions with the new histogram chart type in Langfuse custom dashboards. June 28, 2025 June 28, 2025 Agentic Onboarding & Docs MCP Server Integrate Langfuse into your existing codebase using AI agents like Cursor, Claude Code, GitHub Copilot, and Windsurf. Powered by the new Langfuse Docs MCP server. June 27, 2025 June 27, 2025 Improved JSON Handling in LangChain Prompts Simplified JSON handling in prompts designated for LangChain consumption - no more extra escaping required. June 23, 2025 June 23, 2025 Exports of Datasets and Audit Logs Datasets and Audit Logs can now be exported as CSV and JSON directly from the UI. * Previous * 1 * 2 * 3 * 4 * 5 * Next Was this page helpful? Yes No Support Light Platform * LLM Tracing * Prompt Management * Evaluation * Human Annotation * Datasets * Metrics * Playground Integrations * Python SDK * JS/TS SDK * OpenAI SDK * Langchain * Llama-Index * Litellm * Dify * Flowise * Langflow * Vercel AI SDK * Instructor * API Resources * Documentation * Interactive Demo * Video demo (10 min) * Changelog * Roadmap * Pricing * Enterprise * Self-hosting * Open Source * Why Langfuse? * AI Engineering Library * Status * 🇯🇵 Japanese * 🇰🇷 Korean * 🇨🇳 Chinese About * Blog * Careers * About us * Customers * Support * Talk to us * OSS Friends * Twitter * LinkedIn Legal * Security * Imprint * Terms * Privacy * * SOC 2 Type II * ISO 27001 * GDPR * HIPAA © 2022-2025 Langfuse GmbH / Finto Technologies Inc.

Diff algorithm from the amazing github.com/kpdecker/jsdiff

For now, Differences are performed on text, not graphically, only the latest screenshot is available.

Screenshot requires Playwright/WebDriver enabled

This tool will extract text data from all of the watch history.

RegEx to extract

A RegEx is a pattern that identifies exactly which part inside of the text that you want to extract.

For example, to extract only the numbers from text ‐
Raw text: Temperature 5.5°C in Sydney
RegEx to extract: Temperature ([0-9\.]+)

Be sure to test your RegEx here.

Each RegEx group bracket () will be in its own column, the first column value is always the date.