Microsoft open-sources unit-testing agent that reads repositories and writes tests
code-testing-generator beats stock Copilot by 13.2 percentage points in completion rate on internal benchmark
An AI tool integrated into GitHub that writes code on your behalf. It is the original pioneer that opened the era of the "AI coding assistant." Its flagship features are code autocompletion and a chat-based assistant, installed as an extension in integrated development environments such as Visual Studio Code, Visual Studio, and JetBrains IDEs. The chat-based assistant is used throughout the development process, including explaining code, suggesting bug fixes, and writing test code. In August 2026, "Spec Kit" was released to help developers organize requirements and design before writing code, expanding the tool's scope to intervene from the design stage prior to implementation.
Current rank (1M)
9
Rank over the last 30 days
2026.08.18 – 2026.09.16 · High 7 · Low 18 · Now 9
code-testing-generator beats stock Copilot by 13.2 percentage points in completion rate on internal benchmark
AgentCore-hosted agents call MCP servers on users' laptops without VPNs or open ports
Typing / in the chat window covers everything from planning to switching sessions
Combines Agent Skills packaging and MCP server configuration into a single reusable format across agent clients
The GitHub Copilot usage metrics API has added the ability to track agent app activity per individual agent. The change applies to both daily and 28-day reports at the enterprise and organization levels.
That's the last story.