Cursor Agent SDK: Build, Test, and Deploy AI Agents as Code
Cursor's new Agent SDK lets you define AI agents as folders of Markdown and TypeScript, test them with evals, and deploy to managed ...
Rystic: Test AI Agents Against Real API Simulators
Rystic ships stateful simulators of Slack, Stripe, GitHub, and 12 more APIs for testing AI ...
Microsoft Scope: Test AI Coding Agents Against Your SDK
Your SDK works perfectly for human developers. Clean docs, sensible defaults, a clear upgrade path. ...
GPT-6.1 Terra: 3x Faster, 10x Cheaper Than Astra
OpenAI's GPT-6.1 Terra lands at $1/M tokens with Astra-level performance, a Critical security rating, and ...
GitHub Copilot HydraFusion Max: Watch Your Bill
GitHub added HydraFusion Max to Copilot on Oct 14. Here is what changed, how the ...
Cloudflare Clef-omni: Multimodal Decisions via Audio, Video, and Text
Cloudflare shipped Clef-omni on October 9 — a 30B mixture-of-experts model that makes structured decisions about audio, video, images, and text in a ...
Apple Touchscreen MacBook Pro: What Developers Must Test Now
Apple's first touchscreen MacBook Pro ships tomorrow with zero official touch APIs or HIG guidance. ...
Google Open-Sources TorchTPU: PyTorch on TPUs Without Rewriting Code
Google and Meta open-sourced TorchTPU, letting PyTorch models run on Cloud TPUs with a one-line ...
Claude Duet: Anthropic’s Proactive Agent at $20 vs Dots at $100
Anthropic launched Claude Duet on Oct 21 — a proactive agent on Opus 5.5 with ...
Daytona Gets $60M to Build the Cloud Layer AI Agents Need
Daytona raised $60M at $1B to build agent-native cloud infrastructure. Writer runs 300K sandboxes/day. Here ...