JetBrains AI

Part 3 of a series where we take public "token saver" add-ons for coding agents and run the same paired A/B benchmark against each of them. Part 1 was the caveman skill (advertised −65%, measured −8.5%). Part 2 was rtk (advertised −60–90%, measured +7.6%). We ran 80 paired tasks to test the pony…

Does "rtk" reduce Claude Code token usage? Part 2 of a series where we take public “token saving” add-ons for coding agents and run the same paired A/B benchmark against each of them. Part 1 was the caveman skill (advertised −65%, measured −8.5%). TL;DR: rtk advertised saving: 60–90%. Measured…

A paired A/B benchmark of the token-compression skill Caveman on Claude Code, run on SkillsBench: does it actually save tokens, and does it degrade AI agent output quality? Advertised saving: 65%. Measured saving: 8.5%. Output-token saving on real agentic tasks, with the skill forcibly activat…

Born out of a deep partnership between JetBrains and GitHub, this integration makes Copilot native in the agent picker and delivers a more stable agent experience directly in the IDE you already use every day. From ACP Registry to native experience Copilot was previously accessible via the…

443 developers applied. 39 projects shipped. Here's a deepdive on the finalists and their projects presented at the JetBrains X Codex Hackathon in San Francisco.

443 developers applied. 39 projects shipped. Here's a sneak peak at everything that went down at the JetBrains X Codex Hackathon in San Francisco.

Cursor is now available as an AI agent inside JetBrains IDEs through the Agent Client Protocol.

Together with Zed, we've launched the official ACP Registry: a directory of AI coding agents, integrated directly into JetBrains IDEs.

Hey! Here at JetBrains, we're always happy to bring our users the best and most popular tools available on the market. This has been true for decades with conventional dev tooling: compilers, debuggers, build tools, etc; in the past several years, we've shipped all the newest LLMs in the same man…

JetBrains AI Assistant just got a major upgrade, giving you smarter completions, better project understanding, and more control over how AI works in your IDE.

This summer, we're making Mellum, our code completion model, easier for developers to use locally, and we’re introducing support for more languages than ever.

AI agents are already in your tools—now it’s time to understand them. Learn to build and work with them responsibly in this free course by JetBrains and Nebius.