AI Agents news and analysis on Web Pulse: 38040 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Agentbox, a GitHub project by developer madarco, enables running multiple AI agents in parallel inside isolated sandboxed virtual machines on either a local PC or cloud infrastructure from a single command, according to …
Cursor released a Projects feature and a self-hosted machines capability that lets developers run coding-agent workloads on their own infrastructure instead of only in Cursor's default environment, according to the compa…
Pizza Bot released a self-hosted desktop application for Mac, Windows, and Linux that runs AI agents in the background behind an email-like interface for reviewing completed work and approvals, built on DeepAgents and La…
Skillsynch released txcript, a Rust library and CLI tool that converts and transfers agent sessions between Claude Code, Codex, OpenCode, and Cursor, preserving messages, reasoning, and tool history where the target plat…
Hermes Agent, the open-source autonomous AI agent from Nous Research, starts its web dashboard on 127.0.0.1:9119 by default, and the official documentation identifies a loopback bind reached through an SSH tunnel as an a…
A developer has launched Radio, a provider-agnostic communication layer that lets AI agents from different vendors and machines join a single shared conversation via a URL. Built as a core primitive of the team's Fractal…
SmartBear has made its BearQ agentic QA system available as an assignable testing agent in Atlassian Jira, following BearQ's March launch, letting teams set autonomy levels for autonomous testing of agentic software deve…
Riverbed launched NPM 360, a network performance management product that integrates the agentic AI capabilities of Riverbed IQ and Q into its AppResponse and NetProfiler tools, with NPM+ extending visibility across remot…
XAI launched Grok Voice on fal.ai, giving developers a real-time speech-to-speech API with response latency around 0.70 seconds, support for over 25 languages, 26 voice options, and audio cloning. Pricing is set at $0.00…
A developer running 84 containers across two servers as a one-person company described a self-healing setup built from three bash scripts totaling just over a thousand lines, designed to handle infrastructure failures th…
Unity Technologies launched the Unity CLI, a self-contained command-line binary for managing Unity, alongside the experimental Unity Pipeline package (com.unity.pipeline), according to a beginner's guide by Unity Technol…
Google has launched Agent Anomaly Detection in Private Preview on the Gemini Enterprise Agent Platform, a reasoning-based oversight and audit layer that examines agent reasoning traces, tool calls, and execution flow to …
Axelera AI launched its Europa AI Processing Unit architecture, now available in three form factors and reaching up to 629 TOPS at a 45 W TDP. The Edge 232p single-chip card hits 83.4 tokens per second on Qwen 30B, while…
A developer published an initial provisioning specification and compose templates on GitHub for running local LLMs, Open WebUI, and dev agents in isolated rootless containers with direct GPU acceleration. The specificati…
Cortex Protocol launched an open-source Layer-1 blockchain, ticker $CTX, designed to cryptographically anchor and verify autonomous AI agent states by keeping vector search off-chain while settling 32-byte Merkle state r…
Spotify detailed four quality and reliability problems it faced as AI accelerated its engineering velocity, including a June 24 content-ingestion incident where a scheduling bug cut throughput by about 10% and delayed ep…
NeuroGrid released nrgrd, a terminal user interface coding agent that connects to any OpenAI-compatible inference endpoint, including NeuroGrid Marketplace deployments, vLLM, Ollama, and LM Studio. The tool runs an itera…
BNY CEO and Chairman Robin Vince said the bank's AI platform Eliza, named after Alexander Hamilton's wife Elizabeth Schuyler Hamilton, now understands aspects of the company "probably better than any human being could," …
A developer released Padwan-LLM, a lightweight async Python client that unifies access to OpenAI, Gemini, Mistral, Grok, Anthropic, and any OpenAI-compatible API through a single interface. The package ships with one run…
Anthropic announced on September 17, 2026 that it is merging its Claude Cowork and chat products into a single Claude experience, rolling out to Pro and Max plans over the next few weeks on web, desktop, and mobile, with…