vibehacker
News
Android Developers Blog ·

Android Studio Rabbit 2 goes stable with Bring Your Own Agent: plug in Claude, Codex or 40+ ACP agents

Released Oct 28 at Android Dev Summit, any Agent Client Protocol agent, including Claude Agent, Codex, Junie and Antigravity, can now run inside Android Studio with access to the emulator, build system, Logcat and Android skills, signing in with your own subscription or API key (Settings > Tools > AI > Agents). The release also adds an AI Change Review for walking through large agent-written diffs.

Read at developer.android.com

More news

View all

Copilot in JetBrains gets GA local sandboxes and Fusion model routing

Announced Oct 28, commands that Copilot starts in JetBrains IDEs can now run in a GA local sandbox that limits filesystem, network and credential access by your or your org's policy. The same update brings Fusion, which replaces Auto and picks models per task at Standard, High or Max effort (30% off for 30 days), plus per model token usage when you hover an agent turn…

GitHub Changelog

Copilot cloud sessions go GA: start a task on your phone or in Slack, finish it in VS Code or the CLI

Announced at Universe on Oct 28, one cloud agent session now follows you across github.com, GitHub Mobile, Slack, Teams, the Copilot app, VS Code and Copilot CLI ( /sessions , Remote tab), running in a snapshotting sandbox with no one hour cap. On paid plans, sandbox compute now comes out of your included Actions entitlement, which becomes one dollar based pool shared with your builds…

GitHub Changelog

Microsoft opens the Copilot harness behind VS Code and Copilot CLI to Foundry agents, in preview

Announced Oct 28, Foundry Agent Service can now run your agent on the same managed loop and sandbox as GitHub's Copilot products, with skills, MCP tools and 20+ models; you pick it at agent creation and can't switch later. Runtime is free until Dec 1, then $0.0994 per vCPU hour plus model costs, and the GitHub Copilot SDK is being renamed Microsoft Copilot SDK (changelog)…

Official Microsoft Blog

GitHub Agentic Workflows goes GA: write Actions automations in Markdown and let a coding agent run them

Announced at Universe on Oct 28, you describe tasks like issue triage, CI failure analysis or test writing in a Markdown file, and gh aw compiles it to standard Actions YAML powered by Copilot or your own coding agent, running read only by default in a sandboxed container with a threat detection job checking proposed changes. GA adds self hosted ARC runners, per workflow model choice and routing, micro VM isolation, and gh aw forecast for estimating AI credit spend…

GitHub Changelog

Spotted something we missed? Start a thread.