Microsoft Introduces run-assert-eval for AI Agent Risk Management
Microsoft has released run-assert-eval, a new skill designed to automate risk discovery, policy generation, and evaluation for AI agents.
Read more →
Gitea Releases Runner v4: Shared S3 Cache and Faster CI/CD with Built-in Actions
Gitea has released version 4.0.0 of its runner, introducing S3-compatible caching, built-in actions, and improved observability via OpenTelemetry.
Read more →Anthropic Introduces New Plugin Submission Portal for Claude
Anthropic has launched a new developer portal to streamline the submission, review, and analytics process for plugins in the Claude directory.
Read more →
Google Introduces a Dedicated Planning Mode to Antigravity 2.0
Google has updated its Antigravity platform to version 2.0, adding a dedicated /plan command for structured codebase exploration and implementation planning.
Read more →
Claude Code Introduces Graceful Exit Feature for Usage Limits
Claude Code now allows for a graceful termination of tasks when hitting session time limits, rather than cutting off mid-edit.
Read more →
Docker Launches Cloud Sandboxes for Long-Horizon AI Agents
Docker introduces Cloud Sandboxes to support autonomous coding agents with managed, always-on infrastructure for extended tasks.
Read more →
Google Adds Local AI Model Support to the Antigravity SDK
Google has updated the Antigravity SDK to support local model execution using LiteRT, enabling offline agentic workflows with Gemma 4 26B.
Read more →
Cloudflare Introduces Worker Previews for Isolated Environments
Cloudflare has launched Worker Previews, providing isolated environments for testing code changes per Git branch with independent configurations and state.
Read more →
OpenAI Launches GPT-6 Sol and Luna: Astra-Level Performance at Half the Cost
OpenAI has introduced two new models to the GPT-6 lineup, Sol and Luna, designed to provide faster and more affordable performance for scalable applications.
Read more →Anthropic Introduces Claude Opus 5.5: An AI Model Built for Long-Running Agentic Coding
Anthropic has released Claude Opus 5.5, a new model focused on agentic coding and knowledge work, offering reduced costs and improved performance.
Read more →