--- title: "Langfuse August Update" description: "Langfuse August Update: New Observation Types, End-to-End Walkthrough Videos, Agent Demo Project, and more." ogImage: /images/blog/2025-08-31-langfuse-august-update/august-update.png tag: update date: 2025/08/31 author: "Marc" --- This month, we've shipped updates to improve tracing for complex agents, enhance team collaboration, and expanded the integration library. Here's what's new: ## New Observation Types ![observation types](/images/blog/2025-08-31-langfuse-august-update/observation-types.png) We've introduced new observation types to give you deeper insight into your agent's behavior. You can now semantically label spans as **Agent, Tool, Chain, Retriever, Embedding, and Guardrail**, making it easier to debug and analyze complex traces. For most agent framework integrations, these types are detected automatically. You can also set them manually via the Langfuse Tracing SDKs. → **[Learn more in the docs](/changelog/2025-08-27-enhanced-observation-types)** ## End-to-End Walkthrough Videos ![demo video](/images/blog/2025-08-31-langfuse-august-update/demo-video.png) We've released many new capabilities over recent months. We recorded four new short videos covering observability, prompt management, and evaluation to help you get up to speed quickly. → **[Explore the example project](/docs/demo)** ## Agent Example Project ![example project](/images/blog/2025-08-31-langfuse-august-update/demo-project.png) Experiment with our revamped interactive example project (langfuse.com/demo) that uses the Langfuse Docs MCP server to help with Langfuse questions. This example uses the new observation types mentioned above. → **[Try the Example](/docs/demo)** ## More August Releases - **[Annotation Queue Assignments:](/changelog/2025-08-07-annotation-queue-assignments)** Assign team members to specific annotation queues to streamline your data labeling workflow. - **[Full-Text Search Across Dataset Items:](/changelog/2025-08-25-full-text-search-for-dataset-items)** Quickly find what you need with full-text search across all items in your datasets. - **[New options in Playground:](/changelog/2025-08-14-llm-calls-provider-options)** We've added support for model parameters, e.g. `reasoning_effort`, `service_tier` - **[Docs available as Markdown (.md) endpoints:](/changelog/2025-08-07-markdown-endpoints-and-copy-button)** Use our documentation pages as context for your coding agents via new `.md` endpoints. ## New Integrations We're excited to welcome new partners to the Langfuse ecosystem: - **[Truefoundry:](/integrations/gateways/truefoundry)** An enterprise-grade AI Gateway and control plane. - **[Byteplus by Bytedance:](/integrations/model-providers/byteplus)** A suite of AI-powered APIs and services. - **[Koog:](/integrations/frameworks/koog)** A Kotlin-based framework for building and running AI agents. - **[Shadeform:](/blog/2025-08-13-evaluating-model-performance-accross-clouds-with-shadeform-and-langfuse)** Deploy inference and training jobs to any cloud provider. ## Community Growth ![community growth](/images/blog/2025-08-31-langfuse-august-update/community-growth.png) We're excited that the Langfuse community has grown to over **15k stars on GitHub**, and our SDKs were downloaded nearly **11.8 million times** in July alone. A huge thank you to everyone who has supported us! → **[See our public metrics](/about#public-metrics)** ## User Highlights **SumUp:** Learn how the global payments company rolled out AI-powered support for 4 million merchants across 35+ markets. → **[Read the whole story](/users/sumup)** --- ## Agent Instructions This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/blog/2025-08-31-langfuse-august-update.md`. ### Querying these docs If the answer is not on this page, query the documentation instead of guessing: - **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question: ```bash curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?" ``` - **Index of every page**: , with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt). ### Before writing Langfuse code - **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results. - **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application. - **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples. - **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .