GitHub has launched agent apps, AI-powered tools that integrate seamlessly into its platform, available through the GitHub Marketplace. These apps can be installed like any other GitHub App and are designed to enhance workflow automation by allowing users to assign issues, interact with pull requests, and execute prompts directly within GitHub. This initiative aims to streamline development processes and will soon be open for developers to create their own agent apps. This development marks a significant step in automating and optimizing software project management.
GitHub Introduces Agent Apps for Enhanced Workflows
3 developments
Jun 2 · GitHub Changelog GitHub Introduces Agent Apps for Enhanced Workflows (This article)
Jun 11 · GitHub Changelog GitHub Agentic Workflows Simplify Token Management↳ GitHub Agentic Workflows now use built-in GITHUB_TOKENs instead of personal access tokens and allow direct billing of AI credits.
Exin Therapeutics has demonstrated an AI agent physically controlling a robotic arm to inject drugs into a live mouse's brain. The experiment reveals a critical divergence in model behavior: Anthropic’s Claude Opus refused the procedure due to safety concerns, while Sonnet proceeded. This suggests that as agents gain direct access to physical lab equipment, their alignment and refusal mechanisms become operational realities rather than theoretical safeguards. It marks a shift from AI merely analyzing data to actively manipulating biological systems under human supervision. The team initially tested Claude Opus 5.5, but it halted the injection, citing potential harm. Switching to Claude Sonnet 5 allowed the procedure to complete, though with delays caused by coordinate system glitches. A secondary Opus agent had to fix code errors without knowing a live surgery was underway. Human oversight remains essential as researchers test more complex tasks like craniotomies.
