AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Developer Paolo Viviani released Cerea, an Apache 2.0-licensed, self-hostable chat and agent frontend for LLMs that works with any OpenAI-compatible inference provider and is designed to pair with his Pystino model gatew…
GPT-6 Astra, released in September, ranks as the best model at the social deception game Blood on the Clocktower, leading Claude Opus 4.6 by about 430 Elo points and winning roughly 92% of games against it, according to …
IMR has launched Sera, an AI site reliability engineering teammate that opens incidents with a probable cause, a confidence score and supporting evidence drawn from alerts, recent code changes in GitHub and GitLab, obser…
A developer building Refmade, a desktop app that visualizes Claude Code and Codex sessions as an office, disclosed that the project ran for 17 days without version control until an agent created a private repository on O…
A developer released x402-kit, a scaffolding tool that generates paid APIs, paid MCP servers and paywalled file stores using the HTTP 402 status code and USDC payments on Base, so AI agents can pay per call without accou…
Panda-Taps-LLC released watchdeck v0.1.0 on 2026-11-04, an Apache-2.0-licensed local tool that maps every Claude Code session on a machine, records each tool call and who decided it, and converts a denial into a rule in …
Prax Data Services has exposed its crypto wallet screening service over the Model Context Protocol at https://mcp.orabrain.com/mcp, letting Claude, ChatGPT, Cursor and VS Code call a screen_wallet tool that returns a ris…
Developer July Metodiev released Lantern Lattice, a command-line tool and MCP server that exposes compiler- and type-checker-resolved call graphs to coding agents, with support for Rust, TypeScript, JavaScript, Python, G…
GitHub announced a new Git storage architecture at GitHub Universe that internal testing showed can support 5,000 concurrent agents on a single repository and 7,200 pushes per second while serving reads with consistently…
Tencent announced the release of Tencent Hy4, its latest-generation large language model, which the company says ranks among the world's leading open-source AI models, with model weights and system cards to follow in the…
A developer audited 569 commits across two AI-assisted research repositories and released Git Provenance Auditor, a tool that scans git history for AI assistance trailers such as Co-Authored-By lines from Claude Code and…
A web developer built and shipped "Organizer," an Android manga reader and encrypted media vault, in under two months using AI code assistants including OpenAI's Codex and Google's Antigravity. The developer established …
Moonshot AI published the full open weights for Kimi K3.1 Pro, a 2.8-trillion-parameter model previously available only through its API since October 23, and its own benchmark table puts the model at 65.7 on Terminal-Ben…
Researchers behind the Alpamayo-R1 autonomous driving project demonstrated a native vision-language-action (VLA) policy that applies safety rules at inference time through attention steering rather than retraining, compl…
Forum users on Level1Techs report that running local LLMs on a Proxmox host with an Nvidia RTX 3090 passed through to a VM works without known blockers, with one user saying their local agents run in a Proxmox VM with "s…
Vespper released v1.0 of its DOCX MCP server, which it calls the only SOTA post-trained model for editing Microsoft Word documents, reporting benchmark results run on GPT-5.6 Sol. In 10 matched comparisons against five a…
ZergAI released ZTC (Zerg Terminal Client) v0.9.0-beta.1, a coding agent harness that plans changes, edits code and runs tests in a project, installable via `npm install -g @zergai/ztc@0.9.0-beta.1` on Node.js 20.19+ or …
Construct built a computer-use agent that falls back to a live cloud browser only when a plain web search or page fetch fails or the page requires interaction, then hands findings to a Linux terminal through workspace Fi…
NVIDIA reported that its Vera CPU outperforms both the fastest and the most energy-efficient x86 CPUs in a 100-megawatt data center comparison, delivering 1.6x more agents per watt than the fastest x86 chip and 2x faster…
Perplexity launched Teammates on November 5th, a persistent agent feature inside its Computer product that lets named agents inherit a user's tasks, skills, memory and tools and work proactively on ongoing jobs without w…