AI news, explained

Tools

Latest articles about tools.

Tools12.11.2026Amazon makes SGLang-Neuron publicly available for serving models on AWS TrainiumSGLang-Neuron, released by RadixArk with Annapurna Labs, is now publicly available via an AWS Deep Learning Container, enabling model serving and RL rollouts with SGLang on AWS Trainium chips.Read article

Tools12.11.2026Four Amazon Bedrock request settings that change inference costsAn AWS walkthrough shows how cache duration, service tier, reasoning effort, and maxTokens change token counts and rates on Amazon Bedrock, with tests on Claude and Nova models.
Tools12.11.2026Tracking and Capping Amazon Bedrock Spend per IAM Principal with CUR 2.0 and AWS BudgetsHow to gain per-identity Amazon Bedrock cost visibility and enforceable spend limits using only AWS-native features: IAM principal attribution, CUR 2.0 or Cost Explorer reporting, and AWS Budgets actions.

Tools12.11.2026Building a Self-Service LLM Gateway with Amazon Bedrock and LiteLLMA walkthrough of a self-service LLM gateway that puts Amazon Bedrock foundation models behind an OpenAI-compatible API using LiteLLM on AWS Fargate, with per-user cost controls and observability.Tools12.11.2026LessonFolk offers free, open-source AI lessons through an AI tutor in your existing chat appLessonFolk is an open-source learning platform that teaches AI through conversational lessons delivered by an AI tutor over MCP, inside the chat application users already have.Tools12.11.2026SPECTRA compresses LLMs roughly 3x on CPU alone, with no calibration stepNeuraCryption published technical documentation for SPECTRA, an engine that shrinks language models between 2.80x and 3.31x without a GPU or calibration datasets. All reported figures are self-reported by the company.

Tools12.11.2026AWS migration guide lets coding agents plan a move to Amazon Bedrock Managed Knowledge BaseAWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS, letting a coding agent plan a move to Amazon Bedrock Managed Knowledge Base and, after approval, build the new resource or a migrated IaC template.

Tools12.11.2026AWS shows how to keep AI agent searches within each user's permissions on Bedrock Managed Knowledge BaseA walkthrough builds a shared internal assistant on Amazon Bedrock AgentCore where a request interceptor, Cedar policies, ACL awareness and a resource-based policy keep each user's searches within the documents they may view.Tools12.11.2026LMSYS Adds Experimental Unified Memory to SGLang, Raising Hybrid-Model Throughput by Up to 26% in TestsSGLang's new experimental allocator pools GPU high-bandwidth memory for hybrid models like GPT-OSS, Qwen3.5 and Kimi K3 instead of splitting it into fixed partitions, and single-H200 tests show up to 26% higher throughput.

Tools12.11.2026Show HN: Datatomcp, a data layer where AI agents propose business definitions and people approve themA new Show HN project, datatomcp, pitches itself as an AI-native data layer: databases, sheets and apps are linked once, a person approves the definitions agents use, and every agent question is audited.

Tools12.11.2026agent-access-review: user access reviews for AI agents and MCP serversAn open-source Python tool that inventories AI agents and MCP servers, tests their permissions against a control catalog, and produces auditor-ready evidence, including OSCAL results mapped to NIST 800-53, SOC 2, AI RMF and OWASP.

Tools12.11.2026Vibetime tracks what AI coding sessions actually shipVibetime is an MIT-licensed CLI that wraps AI coding tools, measures git activity, scores sessions, and can submit qualifying work to an opt-in leaderboard.