Follow the latest coverage, related explainers and connected technology stories.
JetBrains proposes evaluating coding agents beyond task-resolution rates by analyzing efficiency, patch quality, and execution paths. A comparison of Claude Opus 4.7 and Gemini 3.5 Flash shows that similar final results can conceal major differences in cost, verification, modification scope, and approaches to handling software repositories.
JetBrains has launched Junie Local, which runs the Junie coding agent locally on a Mac using the Qwen3.6-27B model, without sending code or prompts to the cloud. It requires a Mac with an M5 processor and 64 GB of memory, along with a download of approximately 20 GB.
JetBrains explains the changes it made to Junie and the inference engine to run Qwen3.6-27B locally on M5-powered MacBook devices. The experiment shows that the performance of local coding agents depends on context management and the prefill stage as much as it does on token-generation speed.
The results of the JetBrains Developer Ecosystem Survey 2026 reveal that 90% of professional developers use AI coding agents at work at least once a week, while 68% use them daily. Claude Code leads the field, while Codex is experiencing rapid growth and adoption of GitHub Copilot and Cursor declined between May and July 2026.
JetBrains has added support for the Agent Client Protocol to WebStorm, enabling developers to use multiple AI agents from within the same development environment, including agents associated with their existing subscriptions. The protocol also enables connecting custom agents and controlling the infrastructure and where data is processed.