MLOps news and analysis on Web Pulse: 3506 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
Galdor, a Go-native framework for building and observing AI agents, launched v1.0.0 in June 2026 with built-in OpenTelemetry tracing, an embedded SQLite dashboard, and first-party support for both MCP and A2A protocols. …
A developer building Armorer argues that agent frameworks like LangGraph, CrewAI, and AutoGen create workflows but fail to provide operational visibility. Armorer is a local control plane that generates run receipts capt…
CoreWeave launched unified agentic AI capabilities on May 28, combining serverless reinforcement learning, production inference, fleet observability, and autonomous improvement into a closed feedback loop. The company cl…
Commensa released an open-source tool, commensa-audit, that analyzes GitHub repositories to measure the percentage of engineering effort spent correcting AI-generated code. The company's own audit of 162 PRs found that 2…
Traditional SLOs based on availability, latency, and error rate fail to capture quality failures in probabilistic AI systems, where a response can be fast and technically successful yet produce wrong or harmful output. E…
MLflow, the open-source MLOps platform originally created by Databricks, has evolved into MLflow 3.x to manage the lifecycle of machine learning and AI models, including LLMs and multi-agent systems. It provides tracking…
TensorZero, an open-source LLMOps platform that raised $7.3M in seed funding, archived its repository overnight. The platform provides tools for LLM gateway, observability, evaluation, optimization, and experimentation, …
An engineer details how to implement tail sampling for LLM application traces to control observability costs while preserving critical data. The approach uses OpenTelemetry's tail sampling processor to keep traces with e…
LiteLLM is a powerful open-source proxy for 100+ LLM providers, ideal for prototyping and small-scale deployments. However, as teams scale to production, they may encounter operational overhead from required Redis and Po…
A developer released model-due-diligence, an open-source Python CLI tool that performs static supply-chain security checks on local AI model files and repositories before they are imported into runtimes like Ollama or ll…
A developer argues that embedded SDKs for AI agent reliability outperform proxy gateways by eliminating network latency and operational overhead. The comparison shows embedded SDKs add ~0ms latency versus 30-200ms for ga…
An analysis of 10,000 production LLM calls reveals a 5-15% first-attempt failure rate, with timeouts, rate limits, and schema violations being the most common issues. The NeuralBridge project proposes a self-healing appr…
Data engineering is the development and maintenance of systems that produce high-quality, consistent information from raw data, supporting downstream use cases like analysis and machine learning. The discipline follows a…
A developer's six-month experiment with local LLM inference using Ollama reveals that while it is a compelling demo and research tool, it is a terrible production architecture for most teams. The hidden costs include exp…
An engineer has identified a critical gap in observability for AI agents: standard application logs fail to capture the model's decision-making process. The engineer proposes a trace-based system that records each step o…
A developer at MartinLoop identifies unbounded retry loops as the primary cost driver in AI agent failures, arguing that repeated attempts under unchanged conditions compound mistakes rather than resolve them. The team i…
A developer built a resilient fallback pipeline for AI API calls after a three-hour outage of their primary summarization API took down their meeting transcript tool. The solution uses a router that tries multiple AI cli…
GitHub has launched Agentic Workflows in public preview, integrating AI agents into GitHub Actions by compiling natural language Markdown into standard YAML workflows. The key architectural decision is placing agents wit…
A developer instrumented his autonomous AI agent fleet with full observability after weeks of operating them as black boxes. The system captures metrics from two execution environments—launchd schedules and Cowork sessio…
A Hacker News user asks how developers design human review for production AI agents, specifically what actions are automated versus requiring human approval and how to keep the process auditable. A commenter notes that t…