InfoQ Homepage News
-
Cloudflare Builds High-Performance Infrastructure for Running LLMs
Cloudflare has recently announced new infrastructure designed to run large AI language models across its global network. As these models rely on costly hardware and must handle large volumes of incoming and outgoing text, Cloudflare separates the model's input processing and output generation onto different optimized systems.
-
DuckLake 1.0: Data Lake Format with SQL Catalog Metadata
DuckDB Labs recently released DuckLake 1.0, a data lake format that stores table metadata in a SQL database rather than across many files in object storage. The first implementation is available as a DuckDB extension and includes catalog-stored small updates, improved sorting and partitioning options, and compatibility with Iceberg-style data features.
-
JobRunr Introduces ClawRunr, an Open-Source Java AI Agent
JobRunr has introduced ClawRunr, an open-source Java AI agent for scheduled, recurring, and one-off background tasks. Formerly JavaClaw, it runs on users' hardware and combines conversational interaction with persistent task execution, MCP tools, browser automation, and web, Telegram, and Discord channels, while using JobRunr for scheduling, retries, and monitoring.
-
Confluent Moves Schema IDs to Kafka Headers to Simplify Schema Governance
Confluent introduces a new approach in Apache Kafka that moves schema IDs from message payloads to record headers, aiming to simplify schema governance and evolution. The update integrates with Schema Registry, improves compatibility across serialization formats, and reduces coupling between data and metadata in event-driven architectures.
-
Meta Deploys Unified AI Agents to Automate Performance Optimization at Hyperscale
Meta has unveiled a new AI-driven capacity efficiency platform that uses unified AI agents to automatically detect and resolve performance issues across its global infrastructure, marking a significant step toward self-optimizing systems at hyperscale.
-
Vitest 4.1: Test Tags, Native Node.js Execution and AI Agent Reporter
Vitest 4.1, developed by VoidZero, enhances JavaScript testing with features like test tags for filtering and configuring tests, an experimental mode to bypass Vite's module runner, and new lifecycle hooks. It supports Vite 8 from the start. Notably, it reports improvements in performance compared to Jest. The release addresses issues and provides guides for migration.
-
Broadcom Donates Velero to CNCF, Shifting Kubernetes Backup to Community Governance
Broadcom has announced the contribution of Velero, its Kubernetes-native backup, restore and migration project, to the Cloud Native Computing Foundation (CNCF) as a Sandbox project. Velero It operates at the Kubernetes API layer, capturing cluster state through Custom Resource Definitions (CRDs) rather than through hypervisor or storage-layer snapshots.
-
NVIDIA Launches Ising Open Models for Quantum Computing
NVIDIA has announced a new family of open models called NVIDIA Ising, designed to address quantum processor calibration and quantum error correction. These are two of the main engineering challenges limiting the scalability of current quantum systems, where noise and instability in qubits reduce the reliability of computations.
-
NestJS v12 Roadmap: Full ESM Migration, Standard Schema Validation and Modernised Toolchain
NestJS has announced a draft pull request for its upcoming v12.0.0 release, scheduled for early Q3 2026. Key changes include a transition from CommonJS to ESM, native Standard Schema support in route decorators, and shifts in testing and linting tools. Vitest will replace Jest, and oxlint will replace ESLint, while Rspack will replace Webpack for bundling.
-
Driving and Measuring the Impact of Platform Engineering
Platform engineering has to be approached from a socio-technical perspective, and shaped by all stakeholders, not just developers, Sergiu Petean said in his talk Driving the Future of Insurance through Platform Engineering. Platform success depends on written principles that endure change while embracing change as the main design force, to enable teams to build, run, and release software.
-
Cloudflare Announces Agent Memory, a Managed Persistent Memory Service for AI Agents
Cloudflare announced Agent Memory in private beta, a managed service that extracts structured memories from AI agent conversations and retrieves them on demand using five-channel parallel retrieval with Reciprocal Rank Fusion. Shared memory profiles let teams of agents access common knowledge. Competitors include Mem0, Zep, LangMem, and Letta.
-
Meta's Approach to Migrating their Systems to Post-Quantum Cryptography
Meta has already begun preparing for the threats posed by quantum computing and migrating its systems to post-quantum cryptography, a complex process that will take multiple years to complete. In a recent article, Meta researchers outline their strategy and share key lessons learned along the way.
-
Dropbox Redesigns Compaction to Reclaim Space from Underfilled Storage Volumes
Dropbox recently explained how it improved storage efficiency in Magic Pocket, the company's internal immutable blob store for storing user files at scale, by redesigning compaction strategies to reclaim space from severely underfilled storage volumes. The system now periodically reorganizes valid data into new volumes, allowing old, partially used ones to be cleared and reused.
-
Vercel Releases Open Agents to Support Background AI Coding Workflows
Vercel has launched Open Agents, an open-source app that enables the creation and execution of background coding agents. It provides a complete stack for developers to run independent coding workflows without relying on local machines.
-
Netflix Scales "Human Infrastructure" to Manage Global Live Operations
Netflix has introduced a "human infrastructure" layer to manage live broadcasts at scale. Using a low-latency "telemetry hot path" and a Live Operations Centre, the company now balances automated scaling with human oversight. This shift, which mirrors strategies at AWS and Disney+, focuses on maintaining reliability through expert intervention during high-concurrency global events.