🎉 Kotlin turns 15 this year! 🎉
As part of the celebration, we've brought the Kotlin Effect into real life – making everyday situations more concise, efficient, and fun.
Explore the Kotlin Effect further: https://t.co/5R6adelIfq
Mellum started with code completion.
Mellum2 is built for more – handling both natural language and code.
A 12B-parameter open-source LLM for routing, RAG, and sub-agents, optimized for ultra-low-latency inference.
Now on @huggingface.
Learn more: https://t.co/28sG8Ql52L
Agents can't read your mind. Air helps you provide them better context.
Type @ to mention specific files, folders, symbols or commits in your project.
Or select specific lines of code and click Add to Task to reference them to the agent.
Agentic AI speeds up code production, but the challenge is execution and control.
JetBrains Central is an open system for agentiс development across the SDLC, with governance, observability, and controlled execution.
Early access starts in Q2 2026.
Learn more: https://t.co/k0gDXhXuf6
Writing code isn't the hard part. Creating a productive workflow is.
Air offers parallel, isolated execution, full-project review, and support for Codex, Claude Agent, Gemini CLI, and Junie – all in one place.
Building with agents?
Download Air for free: https://t.co/mYHt6i4sa5
Codex now runs inside @jetbrains IDEs
Plan, write, test, review, and ship code without leaving your code editor
Starting today, you can use Codex with your ChatGPT plan in IntelliJ, PyCharm, WebStorm, and Rider, powered by GPT-5.2 Codex
Join our December 16 livestream to see how AI-driven prototyping turns ideas into working code. Discover how PMs, designers, and developers can work together more efficiently with Matter.
Register now: https://t.co/PpXLfxgEAP
JetBrains is joining the new Agentic AI Foundation, hosted by @linuxfoundation, to contribute to the next generation of open, transparent, and interoperable agentic technologies. AAIF will take stewardship of projects including MCP, goose, and https://t.co/TDS1KhQ0ZZ. https://t.co/vG6CliC6LZ
Cline + @jetbrains . Your favorite AI agent, native in your favorite IDE. Daniel ( @NighttrekETH) , Francis ( @inferencetoken), and Rashad from the Cline team are at re:Invent all week. DM us to chat and meet us on Dec 4th at JetBrains booth with exclusive swag.
🚀Gemini 3 Pro is now live in JetBrains IDEs! It powers AI Chat today – and will soon be available in Junie, our coding agent.
Expect deeper reasoning, stronger instruction following, and multimodal understanding.
Try it today! 🔗 https://t.co/Ga7UweZ9i6
@OpenAIDevs is cooking again: GPT-5.1 performed very well in our first tests!
Photo of an espresso machine → "make it a stylized 2.5D version" → done faster than you can pull a good shot of espresso. Handles ambiguous prompts fast and effectively and the responses also feel more like talking to a coworker.
Try it in JetBrains AI Assistant and Junie today!
🤝JetBrains and Zed are joining forces to advance the Agent Client Protocol (ACP) – an open standard that lets any compatible AI coding agent work inside any editor.
🔗 Read more: https://t.co/4XEI3GbHyt
Claude Agent is now available in your JetBrains IDE’s AI chat!
✨ The new agent leverages @AnthropicAI models, including the freshly released Claude 4.5 Sonnet.
✨ No extra plugins. No extra subscriptions. Just advanced AI coding built in.
Learn more 👉 https://t.co/EfUu5jQehx
More choice in agentic coding – right inside your JetBrains IDEs.
We strive to deliver industry-best AI, so we’re welcoming Cline to our platform – a transparent, client-side coding agent you can use in your IDE.
Check it out: https://t.co/xl0wNfl4IY
The PyCharm team just made debugging AI agents way easier.
The new AI Agents Debugger in PyCharm 2025.2 lets you trace LangGraph workflows, visualize agent behavior, and understand how your AI logic works under the hood.
▶️ Watch the walkthrough: https://t.co/jeP9oG43NJ
Launching Kineto by @jetbrains — an AI-powered no-code platform for building real-world apps.
Real apps is never a one-shot process — it’s 100s of micro-iterations.
Kineto compresses that into an autonomous, multi-agent pipeline, so you can build with zero engineering overhead.