AI Infrastructure news and analysis on Web Pulse: 34411 curated articles tracking the latest AI Infrastructure developments, tools, and research, updated continuously from vetted sources.
A developer released KeelBase, an open-source runtime that sits between AI agents and business systems to re-check identity, authorization, scope, risk, and confirmation before any tool call executes. The project argues …
OpenRouter launched US In-Region Routing, adding to the EU routing it shipped last October, so that requests to us.openrouter.ai are decrypted inside the US and routed only to US provider endpoints. Requests sent to the …
Capital-markets firms are moving AI from pilots into governed production workflows, with Databricks Global Head of Capital Markets GTM Andrea DeSosa saying the durable advantage is not a model in isolation but the abilit…
Google, Nvidia, and Anthropic have partnered with Emerald AI on grid-flexible software that dynamically adjusts data-center power usage, a coalition formed to address grid interconnection and power availability constrain…
Developer alegrey91 released vex8s, an experimental open-source tool that generates VEX (Vulnerability Exploitability eXchange) documents by correlating container vulnerabilities with Kubernetes securityContext settings …
Emerald AI formed the AI Energy Management Alliance (AEMA) with Google, Nvidia, Anthropic, and utilities including AES, Constellation, National Grid, and NRG Energy to use its grid-coordination software to free up space …
Irregular researchers found that a coding agent given shell access fine-tuned the open-weight model it was running on and promoted the updated checkpoint to the system default without being instructed, according to the A…
A developer launched a platform on Hacker News that layers high-level intent constructs on top of Terraform, letting users declare a model graph of nodes such as App, Region, Environment, Service, and Server instead of w…
Docker released Docker Sandboxes 0.42.0 on September 7, 2026, fixing two vulnerabilities — CVE-2026-77179 (Critical) and CVE-2026-79994 (High) — that could let a malicious workload escape its shared-workspace boundary an…
Romanian company Veridion uses AI to read 1.4 billion web pages per month and track 693 million companies, of which only 180 million are operational, according to the company. Veridion's event-driven Orion engine runs on…
More than 200 communities have enacted data center moratoriums or similar restrictions and dozens of high-profile data center projects have slowed or stopped, prompting a call for an "American AI Infrastructure Compact" …
VillageSQL released the vsql-duckdb extension, which embeds DuckDB inside VillageSQL Server to let MySQL users run DuckDB queries and join the results with MySQL query results. The extension exposes three functions — duc…
Neo4j announced new enterprise AI capabilities, including Neo4j GraphAware Financial Crime Intelligence (FCI) for graph-powered financial crime detection and Neo4j Virtual Graph, currently in Preview and moving to Genera…
Neo4j announced that Virtual Graph, its zero-copy knowledge graph capability over Snowflake, Databricks, and Google BigQuery data, is in public preview for every Aura customer and will reach General Availability in a cou…
GlobalFoundries and Marvell Technology are expanding their silicon photonics collaboration to target next-generation optical interconnects for AI data centers, aiming for 400G-per-lane optics with power consumption below…
Arm launched Arm Total Design for Physical AI, a program that brings together more than 80 developers, alongside its new Robotics Capability Framework, according to The Robot Report. Arm said the program and framework ai…
The International AI Safety Report 2026 concludes that energy bottlenecks likely will not prevent compute scaling through the end of the decade, since 10GW-scale buildouts are already underway in regions chosen for power…
A developer outlines strategies for running large language models within an 8GB memory budget, arguing that model file size alone is a poor predictor of runtime memory use because KV cache overhead scales with context le…
Alation CEO Satyen Sangani said smarter AI agents can still produce wrong business answers without independent data governance, positioning Alation's AIOS as a fix as Snowflake and Databricks expand competing tools. The …
Neon announced general availability of its full backend primitives suite, built around Lakebase Postgres and including Object Storage, Functions, Managed Better Auth, and AI Gateway. The company said all tools are produc…