Langfuse
PulseAugur coverage of Langfuse — every cluster mentioning Langfuse across labs, papers, and developer communities, ranked by signal.
- 2026-05-16 product_launch Langfuse v4 integration with Ollama for local LLM tracing is released. 来源
6 天有情绪数据
-
Langfuse 教程展示用于追踪和评估的 LLM 流水线
本教程演示如何使用 Langfuse（一个开源平台）为 LLM 应用程序构建完整的可观测性和评估流水线。该指南涵盖追踪、提示管理、评分和实验执行，提供了一个实用的工作流程。它支持与 OpenAI 或确定性模拟 LLM 集成，允许用户在无需付费模型访问权限的情况下探索 Langfuse 功能。
-
STRIDE-GPT 工具对 AI 应用威胁进行建模，记录上下文，限制令牌
STRIDE-GPT 是一款开源工具，旨在通过分析架构描述来为 AI 应用生成 STRIDE 威胁模型。它强调将 LLM 特定的资产，如系统提示、RAG 文档和代理推理链，作为威胁建模过程中的一等组件来处理。该工具需要详细的架构描述，包括组件、数据流和信任边界，才能生成有效的安全模型。此外，它还强调了全面日志记录对于事后重建的重要性，并提出了分层速率限制策略以防止令牌耗尽攻击。
-
Pingoni adds OpenAI LLM cost tracking for developers
Pingoni has launched a new feature for its API monitoring service that tracks costs associated with OpenAI's LLM usage. This tool allows developers, particularly solo developers and small teams, to monitor their OpenAI …
-
LLM 可观测性平台：Langfuse、LangSmith 与 OpenTelemetry 对比
本文探讨了生产环境中 LLM 可观测性的关键需求，并强调了成本和错误可见性方面的挑战。文章对比了三个领先平台：Langfuse，一个专注于成本归属的开源选项，为某团队节省了每月 400 欧元；LangSmith，Anthropic 为 LangChain 用户提供的集成解决方案，具有强大的根本原因分析能力，但价格上限较高；以及 OpenTelemetry，一个供应商无关的标准，提供最大的控制权，但需要更多仪器化工作。选择取决于具体需求…
-
Langfuse v4 integrates with Ollama for local LLM tracing
A new integration allows developers to trace local large language models using Langfuse v4 and Ollama. This setup, detailed in a blog post and available on GitHub, enables detailed logging of session IDs, user IDs, toke…
-
Glad Labs ships voice agent stability, FinanceModule for cofounder-OS
Glad Labs has released updates for their cofounder-OS, focusing on stabilizing their voice agent and deploying the initial FinanceModule. The voice agent now handles race conditions more gracefully by retrying conversat…
-
AI Agents Risk Budget Overruns and Data Leaks Without Gateways
Running multiple AI agents without proper oversight can lead to significant financial and security risks. Common issues include infinite agent loops that drain budgets due to a lack of delegation depth limits and per-ag…
-
Glad Labs enhances MCP platform with improved error handling and testing
Glad Labs has significantly improved its MCP platform by addressing silent failures and enhancing observability. Key updates include fixing the voice bridge to fail loudly rather than silently, re-enabling previously sk…
-
Developers build LLM observability tools and audit existing setups to track costs and errors
A developer has created a zero-configuration Python tool called llm-lens to monitor API calls to OpenAI and Anthropic, tracking costs, latency, and errors without requiring SDK changes or account setup. The tool uses mo…
-
Langfuse guide covers MLOps concepts, code, and interview prep
This article provides a comprehensive guide to Langfuse, an open-source observability platform for LLM applications. It covers fundamental concepts, practical code examples, and preparation for interviews related to MLO…
-
Skope launches outcome-based billing for AI software, shifting risk to vendors
Skope, a new billing system, has launched to support outcome-based pricing for software products, particularly targeting the burgeoning AI market. The platform allows companies to charge customers only when their softwa…
-
AI初创公司Cekura和Hamming推出语音代理的自动化测试
Cekura和Hamming推出了旨在自动化测试和监控AI语音及聊天代理的平台。这些服务解决了在众多对话路径和复杂场景下手動验证代理性能的挑战。通过模拟真实用户交互并采用基于LLM的评判，这些平台旨在部署前捕获回归问题并确保代理的可靠性，为开发和实时流量监控提供解决方案。