Also reorganised the code to be a bit more focused on SDK and the LLM UI aspect:
CODE
-
Inference Provider App Now Supports Responses API for Open Models
By
–
Inference Provider starter app now supports the Responses API Best part: you can run any open weights model with the Responses API – even if the official provider doesn’t support it. Starter app in the next tweet – check it out!
-
Monitor Cursor Agents Status from Menubar
By
–
Check the status of Cursor’s agents directly from your menubar. pic.twitter.com/IenIpkpGTu
— Cursor (@cursor_ai) 30 septembre 2025Check the status of Cursor’s agents directly from your menubar.
-
Bugbot Rules Now Shareable Across Team
By
–
Rules can now be shared across your entire team. This includes Bugbot rules for automated code reviews.
-
Cursor 1.7 Released: AI Suggestions, Custom Hooks, Team Features
By
–
Cursor 1.7 is now available!
— Cursor (@cursor_ai) 30 septembre 2025
As you type a prompt, suggestions now appear. Press Tab to accept.
Also new: custom hooks, deeplinks, team-wide rules, menubar support, and more. pic.twitter.com/mu7c9AP28RCursor 1.7 is now available! As you type a prompt, suggestions now appear. Press Tab to accept. Also new: custom hooks, deeplinks, team-wide rules, menubar support, and more.
-
Extending Cursor Agent Lifecycle with Hooks and Scripts
By
–
Extend and script every part of the Cursor agent lifecycle with hooks. pic.twitter.com/ZHy22zAUfm
— Cursor (@cursor_ai) 30 septembre 2025Extend and script every part of the Cursor agent lifecycle with hooks.
-
Terminal-Bench: Evaluating AI Coding Assistants Performance
By
–
Why does Terminal-Bench matter?
AI coding assistants (Claude Code, Codex, Cursor, & Devin) rely on command-line interfaces. The terminal represents a convergence of power, flexibility, & the text-based modality where language models excel—hence the need for robust evaluation. -
Designing Safe Agentic Loops: Implementation Guide
By
–
Here's my expanded explanation of what it means to design an agentic loop, how to do it safely (while running in YOLO mode!) and the kinds of interesting problems this approach can be used to tackle
-
Designing Agentic Loops for AI-Assisted Coding Tools
By
–
One of the new skills required to get the most out of AI-assisted coding tools – Claude Code, Codex CLI, etc – is designing agentic loops: carefully selecting tools to run in a loop to achieve a specified goal. Do this well and you can solve many coding problems with brute force.