AI Tools news and analysis on Web Pulse: 51130 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
Developer Renchao Wu published an Open Source Radar roundup of five GitHub Trending projects, led by Vercel Labs' agent-browser, a native Rust CLI that gives AI agents one shell command per browser step, returning pages …
The developer of Bolo, a phone-based speech-to-text app, replaced client-supplied request IDs with a server-side idempotency key built from the device ID plus a SHA-256 hash of the uploaded audio bytes, after logs from 3…
Google released Gemini Omni 1.2 Flash on November 5, 2026, a generally available video generation and editing model that produces 3- to 15-second clips with native audio at roughly $0.07 per second at 720p via the Intera…
A Flutter-based cross-platform AI chat client, built on the llama.cpp wrapper plugin llama_flutter_android, runs GGUF models locally on ARM64 Android phones with Vulkan GPU acceleration while falling back to OpenAI, Anth…
A 2026 analysis of 100,000 paired cold emails found AI-written outreach drew a 4.1% reply rate versus 5.2% for human-written emails, while AI SDR seats sent roughly 7,400 touches per month against 1,150 for human SDRs, a…
A developer published a practical guide to evaluating RAG retrieval, drawing on small reproducible experiments in a public lab repo to show how retrieval metrics behave. The writeup argues retrieval deserves its own eval…
Chessigma released version 1.0.0 of its public chess analysis API, a free interface at https://www.chessigma.com/public-api/v1 that requires no API key, signup, or paywall. The API offers four endpoints — /game to submit…
NVIDIA launched Minerva, an AIOps platform that treats an entire GPU server environment as one interconnected system, pulling live telemetry from GPUs, SuperNICs, cables and workload schedulers to build a dynamic knowled…
Yuxin Zhu of AntV, the open-source data visualization team behind G2 and G6, published a tutorial for building a command-line data analysis agent using the newly released AVA 4.0 framework, DuckDB, and TypeScript. The ag…
DeepSeek released DeepSeek-V4.1-Flash on September 10, 2026, with native multimodal input, a new inference-focused architecture and reduced API prices effective 04:00 UTC that day, and Meta and Reflection answered with o…
A project called Repairer, published by gno.security, has released an open-source Go program that runs on each server and applies a signed stopgap the day a Linux exploit goes public, then automatically removes it once t…
A new arXiv paper (2611.07372v1) introduces EnvOpt, a method for automated end-to-end optimization of stationary agent environments using real or synthetic tasks without graders or reference answers. On AutomationBench, …
Nace AI released Drex, a family of four open-source decision models with 8B (DLM), 9B (v1.5), 35B with 3B active (v2.0), and 27B (Max) parameters that return a probability distribution over user-supplied options without …
Researchers introduced Agent-R$^2$, a real-source data synthesis framework that distills 4,000 task instances from 10,000 web-corpus candidates to train agents on realistic productivity work, according to the arXiv paper…
Anthropic has introduced message threads for its Messages API, an opt-in change that lets clients send only new messages plus a reference to the prior response instead of resending full conversation history. Anthropic re…
The IndiaAI Mission, run under MeitY, released three indigenous foundation models on November 3, 2026: Soket Labs' EKA-1, a 26.3B-parameter sparse hybrid model trained on roughly 7.5 trillion tokens, and ZenteiQ's Dhir 2…
Howseen founder Raphaël Aubry detailed a production MCP server at app.howseen.ai/api/mcp (version 1.3.0) that exposes the company's AI-visibility data to Claude, ChatGPT and Cursor through 44 tools, 26 of them read-only.…
Researchers Edward Misback, Eunice Jun, Erik Vank, Zachary Tatlock and Steven Tanimoto presented Codetations, a VSCode extension that attaches persistent, interactive annotations to arbitrary code spans without modifying…
A new LangGraph example in the open-source schemagate project cuts schema tokens sent to the model by 68% to 78% on a bundled 42-table demo database, sending 489 to 706 tokens per question instead of 2,199, with all thre…
Google released GKE Workspaces on November 4, adding a pause-and-resume capability for GPU notebooks that freezes in-memory variables and loaded model weights while stopping accelerator billing, built on GKE Pod Snapshot…