Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

TestingCatalog AI News
testingcatalog.com > icymi-cursor-announced-projects-for-agent-coordination

Cursor Projects coordinates thousands of coding agents

1+ day, 10+ hour ago   (212+ words) Projects is rolling out in beta to all Cursor users, coordinating features, migrations and recurring maintenance across cloud and local agents. Cursor is rolling out Projects, a beta system that coordinates long-running software work through thousands of delegated agents. Accessible…...

TestingCatalog AI News
testingcatalog.com > google-tests-proper-projects-for-the-gemini-desktop-app

Google tests proper Projects for the Gemini desktop app

6+ day, 8+ hour ago   (286+ words) Google is internally testing Projects for the Gemini desktop app, grouping custom instructions, files and related chats in dedicated workspaces. Google is internally testing a conventional Projects feature for the Gemini desktop app. The working interface lets users create dedicated…...

TestingCatalog AI News
testingcatalog.com > shannon-3-0-ai-pentester-gets-through-aikido-and-xbow

Shannon 3.0 AI pentester gets through Aikido and XBOW

6+ day, 9+ hour ago   (295+ words) TestingCatalog AI News Keygraph has released Shannon 3.0, the third major version of its open-source AI pentester for web applications and APIs. Shannon is a CLI agent that reads an application's source code, works out where it is likely to break,…...

TestingCatalog AI News
testingcatalog.com > ifm-releases-k2-horizon-6-models-with-full-training-record

IFM releases K2 Horizon: six models and full training record

1+ week, 11+ hour ago   (386+ words) TestingCatalog AI News The Institute of Foundation Models has released K2 Horizon, a connected family of six language models ranging from 0.9 billion to 375 billion parameters, published alongside details on how each was trained. The sizes run 0.9B, 3.7B, 7B, 32B, 36B, and 375B, and IFM maps each…...

TestingCatalog AI News
testingcatalog.com > antigravity-2-0-adds-new-vcs-controls-and-a-terminal

Antigravity 2.0 adds new VCS controls and a terminal

2+ week, 5+ day ago   (149+ words) Antigravity 2.0 adds VCS-grounded views for agent, workspace, and branch changes, plus staging, commit tools, and an embedded terminal. Google has added Git version-control controls and an embedded terminal inside Antigravity 2.0, putting repository review and command-line work in the coding assistant’s…...

Google News
testingcatalog.com > fabraix-opens-public-access-for-nyx-ai-security-red-team-agent

Fabraix opens public access for AI security red team agent

3+ week, 4+ day ago   (121+ words) Fabraix opened its second public launch of Nyx, an autonomous red-teaming agent that attacks AI agents to find security holes first. Fabraix has opened a second public launch of Nyx, its autonomous red-teaming agent, positioning the product as continuous security…...

Google News
testingcatalog.com > ornith-1-5-open-models-launch-in-397b-35b-and-9-b-sizes

Ornith-1.5 open models launch in 397B, 35B, and 9 B sizes.

3+ week, 4+ day ago   (370+ words) testingcatalog.com Ornith has released Ornith-1.5, a family of open models that extends the self-scaffolding framework from Ornith-1.0 into a closed self-improvement loop. Where the previous generation wrote the scaffold around a fixed set of human-curated tasks, Ornith-1.5 proposes the…...

TestingCatalog AI News
testingcatalog.com > cursor-begins-origin-code-hosting-rollout-for-paid-plans

Cursor begins Origin code hosting rollout for paid plans

3+ week, 5+ day ago   (283+ words) Cursor began rolling out Origin, built-in code hosting with repositories, pull requests, GitHub sync, and agents, to paid users in early beta. The new Codebase tab is the entry point for Origin repositories. Users select +New, name a repository, and…...

TestingCatalog AI News
testingcatalog.com > anthropic-tests-hub-mode-in-claude-for-sub-agents

Anthropic tests Hub Mode in Claude for sub-agents

3+ week, 5+ day ago   (252+ words) Anthropic is testing Hub Mode in its mobile app, hinting at a future tool for managing agents, though its release timeline is still unknown. Anthropic is working on a new feature called Hub Mode, recently spotted in its mobile app....

TestingCatalog AI News
testingcatalog.com > claude-turns-into-super-app-adding-web-browser-for-cowork

Claude turns into Super App, adding web browser for Cowork

4+ week, 17+ hour ago   (290+ words) Anthropic is developing a built-in browser for Claude Desktop Cowork sessions and a comparison mode to assess Claude model outputs, according to recent builds. Anthropic continues to enhance Claude Desktop, with recent app developments suggesting two potential additions that could…...