# junie

Junie is an AI coding agent by JetBrains that runs in terminals, JetBrains IDEs, GitHub, and GitLab to perform software development tasks.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## JetBrains Air in GoLand: Build, Review, and Profile Go Code With Agents

DevFeed: [JetBrains Air in GoLand: Build, Review, and Profile Go Code With Agents](<https://devfeed.tech/articles/jetbrains-air-in-goland-build-review-and-profile-go-code-with-agents-146493.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/go/2026/11/20/jetbrains-air-in-goland/>)

Author: Dominika Stankiewicz

Published: 2026-11-20T14:13:09Z

Content type: tutorial

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [goland](<https://devfeed.tech/topics/goland.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [air](<https://devfeed.tech/tags/air.md>), [backend](<https://devfeed.tech/tags/backend.md>), [event](<https://devfeed.tech/tags/event.md>), [go](<https://devfeed.tech/tags/go.md>), [goland](<https://devfeed.tech/tags/goland.md>), [handler](<https://devfeed.tech/tags/handler.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [profile](<https://devfeed.tech/tags/profile.md>), [request](<https://devfeed.tech/tags/request.md>), [review](<https://devfeed.tech/tags/review.md>), [services](<https://devfeed.tech/tags/services.md>), [store](<https://devfeed.tech/tags/store.md>), [webhook](<https://devfeed.tech/tags/webhook.md>)

### AI overview

The article demonstrates using JetBrains Air in GoLand 2026.3 to build and verify a signed Go webhook receiver with coding agents. It recommends defining the service requirements first, reviewing agent diffs for security and idempotency issues, and assigning independent follow-up tasks to separate worktrees before combining and checking them with GoLand's HTTP and database tools. Air supports Junie, Codex, Claude Code, and other Agent Client Protocol agents, with session controls for model, effort, and access. The bundled `goland-profiler` skill lets supported agents capture and inspect profiles. In the example, profiling identifies per-request regular-expression compilation in `validateEventID` as the hot path; moving compilation to package initialization yields a reported 4.6x faster benchmark, 59% fewer bytes, and 80% fewer allocations per request, with timing varying by machine.

### Source excerpt

If you've ever built backend services in Go, chances are you've also written a webhook handler or two. They're small and rarely get much attention - that is, until something breaks. A third-party provider sends a signed request, and then you check the signature, store the event, and reply. Sounds like three easy steps, but [...]

## Sky's the Limit: The Cloud9 x JetBrains Global Hackathon Is Back

DevFeed: [Sky's the Limit: The Cloud9 x JetBrains Global Hackathon Is Back](<https://devfeed.tech/articles/sky-s-the-limit-the-cloud9-jetbrains-global-hackathon-is-back-138460.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/blog/2026/11/17/sky-s-the-limit-the-cloud9-jetbrains-global-hackathon-is-back/>)

Author: Roman Prokashev

Published: 2026-11-17T19:02:41Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [Hackathon](<https://devfeed.tech/topics/hackathon.md>), [jetbrains](<https://devfeed.tech/topics/jetbrains.md>), [jetbrains-ai](<https://devfeed.tech/topics/jetbrains-ai.md>), [junie](<https://devfeed.tech/topics/junie.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2026](<https://devfeed.tech/tags/2026.md>), [about](<https://devfeed.tech/tags/about.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [can](<https://devfeed.tech/tags/can.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [games](<https://devfeed.tech/tags/games.md>), [global](<https://devfeed.tech/tags/global.md>), [hackathon](<https://devfeed.tech/tags/hackathon.md>), [here](<https://devfeed.tech/tags/here.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [join](<https://devfeed.tech/tags/join.md>), [limit](<https://devfeed.tech/tags/limit.md>), [love](<https://devfeed.tech/tags/love.md>), [next](<https://devfeed.tech/tags/next.md>), [project](<https://devfeed.tech/tags/project.md>), [projects](<https://devfeed.tech/tags/projects.md>), [results](<https://devfeed.tech/tags/results.md>), [this](<https://devfeed.tech/tags/this.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Cloud9 and JetBrains' global hackathon runs November 17, 2026-January 12, 2027, with a USD 25,000 cash prize pool. Participants choose a VALORANT scouting, League of Legends scouting and draft management, or event minigame project; each entry must use at least one eligible JetBrains tool. GRID esports data is available but optional. Participants receive two months of JetBrains All Products Pack and AI Ultimate access. The article highlights Air in IDEs for working with multiple coding agents, including running them in parallel and reviewing changes with IDE tools; Junie Lite is free until at least December 31, 2026 and does not consume AI credits. Submissions require a public code repository with an open-source license, a working demo or accessible build, a project and tool description, and a video of up to three minutes. Main category winners receive GDC travel and accommodation as well as prizes; full eligibility and prize terms are on the hackathon page.

### Source excerpt

Sky's the Limit is back! Join Cloud9 and JetBrains for the next edition of our global hackathon. Last year, around 2,300 participants registered, and we received 180 project submissions, ranging from coaching tools and scouting assistants to games for fans. You can read about the results and winning projects here. This year, we'd love to [...]

## JetBrains IDEs Transformed for the Agentic Era of Development - With Air

DevFeed: [JetBrains IDEs Transformed for the Agentic Era of Development - With Air](<https://devfeed.tech/articles/jetbrains-ides-transformed-for-the-agentic-era-of-development-with-air-128959.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/ai/2026/11/air-in-jetbrains-ides-ga/>)

Author: Dominique Rolink

Published: 2026-11-11T09:38:53Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [air](<https://devfeed.tech/tags/air.md>), [air-in-jetbrains-ides](<https://devfeed.tech/tags/air-in-jetbrains-ides.md>), [atlassian](<https://devfeed.tech/tags/atlassian.md>), [code](<https://devfeed.tech/tags/code.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-experience](<https://devfeed.tech/tags/developer-experience.md>), [developer-experience-report](<https://devfeed.tech/tags/developer-experience-report.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development](<https://devfeed.tech/tags/development.md>), [experience](<https://devfeed.tech/tags/experience.md>), [experience-report](<https://devfeed.tech/tags/experience-report.md>), [ides](<https://devfeed.tech/tags/ides.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-ai](<https://devfeed.tech/tags/jetbrains-ai.md>), [jetbrains-ides](<https://devfeed.tech/tags/jetbrains-ides.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [release](<https://devfeed.tech/tags/release.md>), [review](<https://devfeed.tech/tags/review.md>), [understand](<https://devfeed.tech/tags/understand.md>), [write](<https://devfeed.tech/tags/write.md>)

### AI overview

Air, available in JetBrains IDEs 2026.3, provides a workspace to run coding agents, track parallel sessions, review changes, and send line-specific feedback while using IDE tools such as inspections, builds, refactorings, database access, and (in IntelliJ IDEA and CLion) debugging. Agents can use separate local Git worktrees, though Air does not yet track worktrees agents create themselves. Air supports JetBrains and third-party agents, with access depending on the provider: a paid JetBrains AI subscription is not required for local agent workflows, and Junie Lite is free with a JetBrains Account; provider charges, limits, and fair-use terms may apply. Claude Code can use a Claude Pro or Max subscription in Air's terminal, while Claude Agent in chat requires JetBrains AI or an Anthropic API key. AI Assistant remains a separate supported plugin until early 2027. Air does not start agents or send code automatically; the developer chooses and authorizes an agent, and subsequent data handling depends on that provider.

### Source excerpt

As agents write more code, individual productivity goes up, but the bottleneck moves to review. 49% of developers now spend four or more hours a week reviewing AI output and correcting prompts (Atlassian State of Developer Experience Report 2026). We believe this means you need to understand what changed, decide whether it belongs in your [...]

## ReSharper 2026.3: Claude Agent and Codex in Visual Studio, .NET 11 and C# 15 Support, and More

DevFeed: [ReSharper 2026.3: Claude Agent and Codex in Visual Studio, .NET 11 and C# 15 Support, and More](<https://devfeed.tech/articles/resharper-2026-3-claude-agent-and-codex-in-visual-studio-net-11-and-c-15-support-and-more-127756.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/dotnet/2026/11/10/resharper-2026-3-release/>)

Author: Mehul Harry

Published: 2026-11-10T21:43:46Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [resharper](<https://devfeed.tech/topics/resharper.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Visual Studio](<https://devfeed.tech/topics/visual-studio.md>), [C#](<https://devfeed.tech/topics/csharp.md>), [.NET](<https://devfeed.tech/topics/net.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [mstest](<https://devfeed.tech/topics/mstest.md>)

Tags: [2026-3](<https://devfeed.tech/tags/2026-3.md>), [acp](<https://devfeed.tech/tags/acp.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [c-sharp-15](<https://devfeed.tech/tags/c-sharp-15.md>), [claude](<https://devfeed.tech/tags/claude.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [junie](<https://devfeed.tech/tags/junie.md>), [net-11](<https://devfeed.tech/tags/net-11.md>), [net-tools](<https://devfeed.tech/tags/net-tools.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [resharper](<https://devfeed.tech/tags/resharper.md>), [resharpercplusplus](<https://devfeed.tech/tags/resharpercplusplus.md>), [runner](<https://devfeed.tech/tags/runner.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

ReSharper 2026.3 adds Claude Agent and Codex alongside Junie in Visual Studio's AI Assistant tool window. They can write and edit code, run terminal commands, explain a solution, and use ReSharper refactorings such as Rename. Claude Agent and Codex require a JetBrains AI subscription and consume its quota; personal Claude or ChatGPT subscriptions and BYOK are unsupported. First use requires consent to install the third-party agent, and ReSharper installs Node.js if needed. The release adds .NET 11 and C# 15 support, including new syntax analysis and assistance, and renders preview runtime-async methods as ordinary async methods in the decompiler. The test runner supports xUnit v3 4.0 and NUnit 5.0, improves MSTest 4 discovery, applies Playwright settings from .runsettings, and enables Microsoft.Testing.Platform by default. The supplied text is an excerpt, so it may not cover all release changes.

### Source excerpt

ReSharper 2026.2 brought Junie to Visual Studio as ReSharper's first coding agent. In 2026.3, you can also pick Claude Agent or Codex in the same tool window. All three agents can use ReSharper's refactoring skill to run refactorings such as Rename. This release also supports .NET 11 and C# 15, and the test runner now [...]

## RustRover 2026.3 Is Out: JetBrains Air, Clearer Debugger Views, and Agents That Debug With You

DevFeed: [RustRover 2026.3 Is Out: JetBrains Air, Clearer Debugger Views, and Agents That Debug With You](<https://devfeed.tech/articles/rustrover-2026-3-is-out-jetbrains-air-clearer-debugger-views-and-agents-that-debug-with-you-119345.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/rust/2026/11/05/new-in-rustrover-2026-3/>)

Author: Irina Mihajlovic

Published: 2026-11-05T15:53:42Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [rustrover](<https://devfeed.tech/topics/rustrover.md>), [junie](<https://devfeed.tech/topics/junie.md>), [jetbrains](<https://devfeed.tech/topics/jetbrains.md>), [jetbrains-ai](<https://devfeed.tech/topics/jetbrains-ai.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [2026-3](<https://devfeed.tech/tags/2026-3.md>), [acp](<https://devfeed.tech/tags/acp.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [air](<https://devfeed.tech/tags/air.md>), [api](<https://devfeed.tech/tags/api.md>), [bug](<https://devfeed.tech/tags/bug.md>), [code](<https://devfeed.tech/tags/code.md>), [debug](<https://devfeed.tech/tags/debug.md>), [debugger](<https://devfeed.tech/tags/debugger.md>), [function](<https://devfeed.tech/tags/function.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [release](<https://devfeed.tech/tags/release.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [rustrover](<https://devfeed.tech/tags/rustrover.md>), [stack](<https://devfeed.tech/tags/stack.md>), [state](<https://devfeed.tech/tags/state.md>), [whatsnew-2](<https://devfeed.tech/tags/whatsnew-2.md>)

### AI overview

RustRover 2026.3 adds JetBrains Air for running and reviewing coding agents, including Claude Agent, Codex, Gemini, GitHub Copilot, Junie, OpenCode, and other ACP-compatible agents; existing subscriptions and API keys work without a JetBrains AI subscription. Debugger views now shorten Rust names by default, with an option to turn this off, and profiler results can jump to source with readable function names on Linux perf and macOS DTrace. A debugger MCP server and rustrover-debugger skill let agents set breakpoints, step, inspect variables, and evaluate expressions through the regular debugger; users can follow or take over. The release also supports remote SSH development with native OpenSSH authentication features, and automatically sends technical error and UI freeze reports with paths, URLs, and usernames removed; reporting can be disabled. Other listed updates include sound cues, copied project configuration for new Git worktrees, a combined plugins view, and Ghostty as the default terminal emulator.

### Source excerpt

Fixing a bug starts with understanding what your code is doing at runtime: reading the program state, following the call stack, or tracking down a slow function. RustRover 2026.3 makes that work easier to follow, whether you do it yourself or with an AI agent. It also ships with JetBrains Air, a new layer for [...]

## RubyMine 2026.3: JetBrains Air, Native Mode for WSL and Dev Containers, and More

DevFeed: [RubyMine 2026.3: JetBrains Air, Native Mode for WSL and Dev Containers, and More](<https://devfeed.tech/articles/rubymine-2026-3-jetbrains-air-native-mode-for-wsl-and-dev-containers-and-more-119344.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/ruby/2026/11/rubymine-2026-3-jetbrains-air-native-mode-for-wsl-and-dev-containers-and-more/>)

Author: Alexey Varfolomeev

Published: 2026-11-05T13:47:45Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [Tool](<https://devfeed.tech/topics/tool.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Windows Subsystem for Linux](<https://devfeed.tech/topics/wsl.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [2026-3](<https://devfeed.tech/tags/2026-3.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [air](<https://devfeed.tech/tags/air.md>), [articles-2](<https://devfeed.tech/tags/articles-2.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [containers](<https://devfeed.tech/tags/containers.md>), [dev](<https://devfeed.tech/tags/dev.md>), [development](<https://devfeed.tech/tags/development.md>), [interpreter](<https://devfeed.tech/tags/interpreter.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [native](<https://devfeed.tech/tags/native.md>), [rails](<https://devfeed.tech/tags/rails.md>), [refactoring](<https://devfeed.tech/tags/refactoring.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [ruby](<https://devfeed.tech/tags/ruby.md>), [ruby-on-rails](<https://devfeed.tech/tags/ruby-on-rails.md>), [rubymine](<https://devfeed.tech/tags/rubymine.md>), [rubymine-2026-3](<https://devfeed.tech/tags/rubymine-2026-3.md>), [support](<https://devfeed.tech/tags/support.md>), [what-s-new](<https://devfeed.tech/tags/what-s-new.md>), [whats-new](<https://devfeed.tech/tags/whats-new.md>), [wsl](<https://devfeed.tech/tags/wsl.md>)

### AI overview

RubyMine 2026.3 adds JetBrains Air, which brings supported coding agents such as Claude Agent, Codex, Gemini, GitHub Copilot, and Junie into the IDE for task runs and change review. Users can connect agents with an existing provider subscription or API key; no JetBrains AI subscription is required. Native mode lets RubyMine work locally with WSL and Dev Container projects while code and Ruby tools remain in Linux, with native interpreters supporting Rails console, Bundler, and tests with coverage. RubyMine also selects interpreters using Gemfile version requirements, recognizes Homebrew Ruby installs, improves Rails load-hook analysis and query workflows, and adds fuzzy class and symbol search plus safer renaming. Git worktree setup can carry project settings, selected files, and setup scripts. The excerpt also describes customizable audio cues and automatic technical error and freeze reports, configurable in Data Sharing settings.

### Source excerpt

RubyMine 2026.3 is out! This release brings JetBrains Air for working with your preferred coding agents, native access to WSL and Dev Container projects, and smarter Ruby and Rails support. You'll also find easier interpreter setup, improved navigation and refactoring, and updates that make everyday development more comfortable. Download RubyMine 2026.3 from our website or [...]

## CLion 2026.3 Is Here

DevFeed: [CLion 2026.3 Is Here](<https://devfeed.tech/articles/clion-2026-3-is-here-119019.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/clion/2026/11/2026-3-release/>)

Author: Oleg Zinovyev

Published: 2026-11-05T11:27:05Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [CLion](<https://devfeed.tech/topics/clion.md>), [CUDA Tile](<https://devfeed.tech/topics/cuda-tile.md>), [CMake](<https://devfeed.tech/topics/cmake.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [jetbrains-toolbox](<https://devfeed.tech/topics/jetbrains-toolbox.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [2026-3](<https://devfeed.tech/tags/2026-3.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [air](<https://devfeed.tech/tags/air.md>), [c](<https://devfeed.tech/tags/c.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [clion](<https://devfeed.tech/tags/clion.md>), [cmake](<https://devfeed.tech/tags/cmake.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [cuda-tile](<https://devfeed.tech/tags/cuda-tile.md>), [dap](<https://devfeed.tech/tags/dap.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [download](<https://devfeed.tech/tags/download.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [ispc](<https://devfeed.tech/tags/ispc.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [news](<https://devfeed.tech/tags/news.md>), [releases](<https://devfeed.tech/tags/releases.md>), [trace32](<https://devfeed.tech/tags/trace32.md>)

### AI overview

CLion 2026.3 adds JetBrains Air for running and reviewing agents, plus agent-assisted workflows for debugging ARM Cortex-M hard faults and diagnosing failed CMake loads. Air supports multiple agents and existing provider subscriptions, API keys, and custom base URLs; free Junie Lite is included with a JetBrains Account. Embedded debugging adds RTOS tasks, queues, and timers to agent tools. Debug profiles can be edited as JSON, with a dedicated TRACE32 launch and attach profile and configurable DAP working directories and environment variables. Language support includes CUDA Tile C++ for C++20 projects using CUDA Toolkit 13.3 or later, ISPC code insight, and automatic compiler headers and macros when no build targets provide settings. The release also adds class memory layout visualization and copies local project settings into Git worktrees. The Classic engine plugin's 2026.3 version is its last stable release; updates end in November 2026.

### Source excerpt

With JetBrains Air, agent-assisted embedded debugging and CMake project setup, plus support for NVIDIA CUDA Tile C++ and ISPC. CLion 2026.3 is now available. This latest version of the JetBrains IDE for C and C++ includes the following key features: You can download CLion 2026.3 from the link below, via the Toolbox App, as a [...]

## Junie Local became 70% faster on Mac M5

DevFeed: [Junie Local became 70% faster on Mac M5](<https://devfeed.tech/articles/junie-local-became-70-faster-on-mac-m5-105693.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/junie/2026/10/junie-local-splash-dflash2/>)

Author: Stanislav Erokhin

Published: 2026-10-28T14:40:49Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>)

Tags: [acceptance](<https://devfeed.tech/tags/acceptance.md>), [acceptance-rate](<https://devfeed.tech/tags/acceptance-rate.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [attention](<https://devfeed.tech/tags/attention.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-tasks](<https://devfeed.tech/tags/coding-tasks.md>), [draft](<https://devfeed.tech/tags/draft.md>), [engine](<https://devfeed.tech/tags/engine.md>), [fast](<https://devfeed.tech/tags/fast.md>), [faster](<https://devfeed.tech/tags/faster.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-engine](<https://devfeed.tech/tags/inference-engine.md>), [jetbrains-ai](<https://devfeed.tech/tags/jetbrains-ai.md>), [junie](<https://devfeed.tech/tags/junie.md>), [local](<https://devfeed.tech/tags/local.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [m5-max](<https://devfeed.tech/tags/m5-max.md>), [mac](<https://devfeed.tech/tags/mac.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

Junie Local reports roughly 70 tokens/s on M5 Max, up from about 40, with bursts to 107; prefill rises from 850 to 1,200 tokens/s, and a 100k context uses about 24 GB of RAM. The gains come from replacing MLX-VLM with Splash, which verifies eight drafted tokens per decode step and reduces context attention cost, plus a DFlash2 drafter fine-tuned on Junie Local coding trajectories for Qwen3.8-3.6-27B-blend. The drafter's acceptance rate depends on how familiar a task is, so speed can vary. The release supports M4 Macs and newer with 64 GB RAM, but M4 prefill is about four times slower than M5. Upgrade with `junie update`, then run `/local` and press `ctrl + r` to update the inference engine.

### Source excerpt

Junie Local now delivers ~70 tokens/s on M5 Max for coding tasks, up from ~40 tokens/s, with bursts up to 107 tokens/s. Two changes made this possible: the Splash inference engine and a new DFlash2 draft model. Back in August, when we first released Junie Local for Mac M5, we spent a lot of time [...]

## Junie Eco Mode

DevFeed: [Junie Eco Mode](<https://devfeed.tech/articles/junie-eco-mode-105692.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/junie/2026/10/junie-eco-mode/>)

Author: Helena Klause

Published: 2026-10-28T12:56:31Z

Content type: article

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [air](<https://devfeed.tech/tags/air.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cost](<https://devfeed.tech/tags/cost.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [junie](<https://devfeed.tech/tags/junie.md>), [model](<https://devfeed.tech/tags/model.md>), [news](<https://devfeed.tech/tags/news.md>), [plan](<https://devfeed.tech/tags/plan.md>), [release](<https://devfeed.tech/tags/release.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

Junie Eco Mode uses the selected model to inspect a code-change task and produce a structured plan, then hands the conversation and plan to a lower-cost model (currently GPT-6 Luna) for implementation and testing. The planning model reads and searches without editing, except that it may add a small reproducing test for a reported bug; questions and other tasks without intended code changes stay with the selected model. Eco makes one handoff and does not switch back. In internal evaluations across 29 configuration pairs on benchmark B and 21 on benchmark A, average model cost per task fell 57.3% and 48.1%, respectively. Average resolve rate fell 0.6 percentage points on B and rounded to 32.1% both with and without Eco on A; individual configurations may differ more. It is available in supported JetBrains IDE builds and Junie CLI 26.10.20+, enabled by default for listed model-and-effort configurations, and unavailable in /remote sessions and some configurations.

### Source excerpt

Not every step of a coding task needs the smartest model in the world. Junie Eco Mode uses your selected model to investigate a coding task and create a plan, then hands implementation and testing to a lower-cost model. In two internal benchmarks, this approach reduced average model cost per task by 48% and 57%, [...]

## Getting Started with Air in JetBrains IDEs - Part 1

DevFeed: [Getting Started with Air in JetBrains IDEs - Part 1](<https://devfeed.tech/articles/getting-started-with-air-in-jetbrains-ides-part-1-105691.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/ai/2026/10/getting-started-with-air-part1/>)

Author: Tanu Tams

Published: 2026-10-28T10:21:42Z

Content type: tutorial

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [jetbrains](<https://devfeed.tech/topics/jetbrains.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Tutorial](<https://devfeed.tech/topics/tutorial.md>), [jetbrains-ai](<https://devfeed.tech/topics/jetbrains-ai.md>), [junie](<https://devfeed.tech/topics/junie.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [acp](<https://devfeed.tech/tags/acp.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [air](<https://devfeed.tech/tags/air.md>), [claude](<https://devfeed.tech/tags/claude.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [github](<https://devfeed.tech/tags/github.md>), [how-tos](<https://devfeed.tech/tags/how-tos.md>), [ides](<https://devfeed.tech/tags/ides.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [jetbrains-ides](<https://devfeed.tech/tags/jetbrains-ides.md>), [review](<https://devfeed.tech/tags/review.md>), [run](<https://devfeed.tech/tags/run.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Air brings multiple coding-agent sessions into JetBrains IDEs, where you can track progress, inspect diffs, run tests, and send feedback to agents. It supports installed or custom agents, including Codex, Gemini, GitHub Copilot, Claude Agent, and Junie; compatible agents can run in chat or terminal interfaces. Install Air through JetBrains Marketplace or use the 2026.3 EAP integration. Installing Air alone does not activate agents or send project code to a provider; connecting a third-party agent sends data directly to that provider under your agreement. A JetBrains AI subscription supports the listed agents, while Claude Agent in Chat view requires that subscription; its terminal interface can use a Claude subscription. Sessions can include file or code context, and Air provides session-level cost estimates. The article also notes Junie Lite is currently available to try without a paid subscription.

### Source excerpt

Setting coding agents up to handle several tasks while you continue working is easy. The harder part is knowing where each task stands, what each agent has changed, and what still needs your attention. Recently, we introduced Air in JetBrains IDEs. It brings coding agents into the environment where you already write, review, run, and [...]

## Coding-Agent Benchmarks Should Match Their Users' Task Flows

DevFeed: [Coding-Agent Benchmarks Should Match Their Users' Task Flows](<https://devfeed.tech/articles/coding-agent-benchmarks-should-match-their-users-task-flows-91169.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/research/2026/10/user-task-flow-paper/>)

Author: Igor Slinko

Published: 2026-10-20T10:27:16Z

Content type: opinion

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Application Development](<https://devfeed.tech/topics/application-development.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [coding-agent-benchmarks](<https://devfeed.tech/tags/coding-agent-benchmarks.md>), [jetbrains-ides](<https://devfeed.tech/tags/jetbrains-ides.md>), [research](<https://devfeed.tech/tags/research.md>), [swe-bench-pro](<https://devfeed.tech/tags/swe-bench-pro.md>), [task-flows](<https://devfeed.tech/tags/task-flows.md>)

### AI overview

Analysis of 4,782 coding-agent sessions in JetBrains IDEs finds that real developer requests include codebase questions, planning, reviews, and other tasks beyond the bug fixes and features that dominate SWE-Bench Pro. The authors argue benchmarks should match a stated user population. Their SWE-TaskFlow method preserves repositories, requirements, and tests while splitting issues into staged requests and adding repository questions. On 700 selected tasks, optimized sequences reached a Task Flow Alignment Score of 77.8 against long JetBrains sessions. Splitting raised per-task cost 2.0-2.6x and changed resolve rates little; repository questions added 4%-24% cost, with answer accuracy of 69.8%-83.0%. The pilot is limited to three runs per setup, lacks human-labeled classifier accuracy data, and does not yet generate several common request types or reactive user feedback.

### Source excerpt

Left: SWE-Bench Pro, where each task is a single user message, almost always a new feature or a bug fix. Right: the first five developer messages in sessions of software engineers working in JetBrains IDEs, counting only sessions with at least three messages. Each column is a message position, colored Cblocks are request types, and [...]

## Junie Local Comes to the NVIDIA RTX Spark

DevFeed: [Junie Local Comes to the NVIDIA RTX Spark](<https://devfeed.tech/articles/junie-local-comes-to-the-nvidia-rtx-spark-88795.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/junie/2026/10/junie-local-rtx-spark/>)

Author: Vladimir Sotnikov

Published: 2026-10-16T13:53:12Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [NVIDIA RTX](<https://devfeed.tech/topics/nvidia-rtx.md>), [NVIDIA Blackwell](<https://devfeed.tech/topics/nvidia-blackwell.md>), [DGX Station](<https://devfeed.tech/topics/dgx-station.md>), [Grace CPU](<https://devfeed.tech/topics/grace-cpu.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [download](<https://devfeed.tech/tags/download.md>), [fp8](<https://devfeed.tech/tags/fp8.md>), [generation](<https://devfeed.tech/tags/generation.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-memory](<https://devfeed.tech/tags/gpu-memory.md>), [grace-cpu](<https://devfeed.tech/tags/grace-cpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [jetbrains-ai](<https://devfeed.tech/tags/jetbrains-ai.md>), [junie](<https://devfeed.tech/tags/junie.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [new-products](<https://devfeed.tech/tags/new-products.md>), [news](<https://devfeed.tech/tags/news.md>), [nvidia-rtx-spark](<https://devfeed.tech/tags/nvidia-rtx-spark.md>), [release](<https://devfeed.tech/tags/release.md>), [rtx-spark](<https://devfeed.tech/tags/rtx-spark.md>), [run](<https://devfeed.tech/tags/run.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

JetBrains says Junie Local is supported on NVIDIA RTX Spark at launch and that Windows support for RTX cards with at least 24 GB of VRAM is now stable. The coding agent runs models locally, reads and edits code, and runs tests; the article describes GPU-sized context windows, FP8 inference and speculative decoding. JetBrains reports an initial RTX Spark performance of up to 55 tokens per second and says further optimizations are in development.

### Source excerpt

Junie Local is supported on the NVIDIA RTX Spark from day one, and Windows support moves from experimental to stable. NVIDIA's RTX Spark platform pairs a Blackwell RTX GPU with a Grace CPU to run larger local AI models in slim laptops and compact desktops. Junie Local leverages this hardware to bring local AI coding [...]

## A New Agentic Experience: JetBrains Air in IDEs - EAP Now Open

DevFeed: [A New Agentic Experience: JetBrains Air in IDEs - EAP Now Open](<https://devfeed.tech/articles/a-new-agentic-experience-jetbrains-air-in-ides-eap-now-open-63459.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/ai/2026/10/air-in-ides-eap/>)

Author: Dominique Rolink

Published: 2026-10-01T12:42:32Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [junie](<https://devfeed.tech/topics/junie.md>), [jetbrains-ai](<https://devfeed.tech/topics/jetbrains-ai.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [development](<https://devfeed.tech/tags/development.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>)

### AI overview

JetBrains has opened early access to Air in its IDEs, offering a plugin and a native option in the 2026.3 EAP builds. Air brings existing coding agents into IDE workflows, with parallel sessions, controls for tracking and reviewing agent work, and optional cloud runs. It is a tool for connecting to agents rather than an AI provider, and users can choose to disable it.

### Source excerpt

Last week, we shared our point of view on where we think agentic development is headed and introduced JetBrains' answer to it: JetBrains Air, an open system of products for agentic development. Today, we're launching the Early Access Program for Air in JetBrains IDEs. It's available now as a plugin on JetBrains Marketplace or natively [...]

## JetBrains Air: Run AI Coding Agents in JetBrains IDEs

DevFeed: [JetBrains Air: Run AI Coding Agents in JetBrains IDEs](<https://devfeed.tech/articles/jetbrains-air-run-ai-coding-agents-in-jetbrains-ides-60204.md>)

Original publisher: [Read original article](<https://laravel-news.com/jetbrains-air>)

Author: Paul Redmond

Published: 2026-09-25T02:20:50Z

Content type: news

Language: en

Sources: [Laravel](<https://devfeed.tech/sources/laravel.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [jetbrains-ai](<https://devfeed.tech/topics/jetbrains-ai.md>), [ide](<https://devfeed.tech/topics/ide.md>), [junie](<https://devfeed.tech/topics/junie.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>)

Tags: [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ides](<https://devfeed.tech/tags/ides.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [news](<https://devfeed.tech/tags/news.md>)

### AI overview

JetBrains announced JetBrains Air, a product suite for running and managing AI coding agents in JetBrains IDEs, team cloud environments, and organizational governance workflows.

### Source excerpt

JetBrains Air runs Claude Agent, Codex, Junie, and other AI coding agents in PhpStorm and other JetBrains IDEs, with team automations and AI cost controls. The post JetBrains Air: Run AI Coding Agents in JetBrains IDEs appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox.

## Making Local AI Smarter and Faster

DevFeed: [Making Local AI Smarter and Faster](<https://devfeed.tech/articles/making-local-ai-smarter-and-faster-55162.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/junie/2026/09/smarter-local-al/>)

Author: Vladimir Sotnikov

Published: 2026-09-18T13:42:27Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [qwen](<https://devfeed.tech/topics/qwen.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [junie](<https://devfeed.tech/tags/junie.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [ml](<https://devfeed.tech/tags/ml.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [token-savings](<https://devfeed.tech/tags/token-savings.md>), [update](<https://devfeed.tech/tags/update.md>), [updates](<https://devfeed.tech/tags/updates.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

This release introduces a blended local coding model for Junie Local by merging Qwen3.6 and Qwen3.8 weights in equal proportions. In an internal 100-task coding benchmark, it completed 37 tasks, compared with 34 for Qwen3.6 with reasoning disabled and 39 for Qwen3.8, while generating 71% fewer output tokens than Qwen3.8. The update also adds experimental NVIDIA support on Windows.

### Source excerpt

We want local coding agents to be smart and fast, with the ability to understand a codebase, do useful work, and finish tasks without long waits. This Junie Local update makes it practical to use a more capable model on your own machine. In the first release, we had to choose between two versions of [...]

## Junie /demo launches apps and records UI checks from the Junie CLI

DevFeed: [Junie /demo launches apps and records UI checks from the Junie CLI](<https://devfeed.tech/articles/your-diff-has-a-demo-now-with-junie-demo-42784.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/junie/2026/09/junie-demo/>)

Author: Aliaksei Kartynnik

Published: 2026-09-18T11:51:27Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [App](<https://devfeed.tech/topics/app.md>), [User Interfaces](<https://devfeed.tech/topics/user-interfaces.md>), [issue tracking](<https://devfeed.tech/topics/issue-tracking.md>), [Docker](<https://devfeed.tech/topics/docker.md>)

Tags: [added](<https://devfeed.tech/tags/added.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [docker](<https://devfeed.tech/tags/docker.md>), [feature](<https://devfeed.tech/tags/feature.md>), [issue-tracker](<https://devfeed.tech/tags/issue-tracker.md>), [junie](<https://devfeed.tech/tags/junie.md>), [testing](<https://devfeed.tech/tags/testing.md>), [tests](<https://devfeed.tech/tags/tests.md>), [ui](<https://devfeed.tech/tags/ui.md>)

### AI overview

Junie /demo is a new Junie CLI mode that builds and launches an app, interacts with its UI, and records the run. It produces an HTML report, screenshots, and a video for review.

### Source excerpt

You have the change ready and the tests are green. Now someone has to launch the app, find the right screen, and check the flow. Often, that someone is still you, even when an agent helped write the code. You should be able to delegate that part too. Junie /demo is a new mode in [...]

## Inside JetBrains--the company reshaping how the world writes code

DevFeed: [Inside JetBrains--the company reshaping how the world writes code](<https://devfeed.tech/articles/inside-jetbrains-the-company-reshaping-how-the-world-writes-code-6523.md>)

Original publisher: [Read original article](<https://openai.com/index/jetbrains-2025>)

Published: 2025-11-25T00:00:00Z

Content type: news

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [jetbrains](<https://devfeed.tech/topics/jetbrains.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [junie](<https://devfeed.tech/topics/junie.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [codex](<https://devfeed.tech/topics/codex.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [also](<https://devfeed.tech/tags/also.md>), [build](<https://devfeed.tech/tags/build.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [company](<https://devfeed.tech/tags/company.md>), [design](<https://devfeed.tech/tags/design.md>), [developers](<https://devfeed.tech/tags/developers.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gpt-5](<https://devfeed.tech/tags/gpt-5.md>), [inside](<https://devfeed.tech/tags/inside.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [software](<https://devfeed.tech/tags/software.md>), [tools](<https://devfeed.tech/tags/tools.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

JetBrains says it is adding OpenAI models to software development workflows used by its teams and customers. Internally, teams use ChatGPT, GPT-5, and Codex; customers can choose GPT-5 in the Junie coding agent and AI Assistant chat. Head of Product Kris Kang reports that agents have successfully completed increasingly difficult assigned tasks, though the excerpt gives no benchmark results. JetBrains judges the approach by both speed--less boilerplate, fewer context switches, faster iteration--and code quality, emphasizing safety, readability, reviewability, and maintainability. Its described workflow keeps people responsible for system design and review while AI assists with drafting and repetitive work.

### Source excerpt

JetBrains is integrating GPT-5 across its coding tools, helping millions of developers design, reason, and build software faster.

## ACP Brings JetBrains on Board

DevFeed: [ACP Brings JetBrains on Board](<https://devfeed.tech/articles/acp-brings-jetbrains-on-board-13509.md>)

Original publisher: [Read original article](<https://zed.dev/blog/jetbrains-on-acp>)

Author: Franciska Dethlefsen

Published: 2025-10-06T00:00:00Z

Content type: release

Language: en

Sources: [Zed Industries](<https://devfeed.tech/sources/zed-industries-blog.md>)

Topics: [Protocol (disambiguation)](<https://devfeed.tech/topics/protocol.md>), [ide](<https://devfeed.tech/topics/ide.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [junie](<https://devfeed.tech/topics/junie.md>), [PyCharm](<https://devfeed.tech/topics/pycharm.md>), [webstorm](<https://devfeed.tech/topics/webstorm.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [codex](<https://devfeed.tech/tags/codex.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [integration](<https://devfeed.tech/tags/integration.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [intellij](<https://devfeed.tech/tags/intellij.md>), [intellij-idea](<https://devfeed.tech/tags/intellij-idea.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [junie](<https://devfeed.tech/tags/junie.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [pycharm](<https://devfeed.tech/tags/pycharm.md>), [vendor-lock-in](<https://devfeed.tech/tags/vendor-lock-in.md>)

### AI overview

JetBrains will co-develop the Agent Client Protocol with Zed and plans to add ACP support across its IDE ecosystem, including IntelliJ IDEA, PyCharm, and WebStorm. The article presents ACP as an open standard intended to let agents work across compatible editors.

### Source excerpt

The Agent Client Protocol reaches a major milestone: JetBrains is committing to bringing ACP support to their entire ecosystem.

## My experience using Junie for the past few months

DevFeed: [My experience using Junie for the past few months](<https://devfeed.tech/articles/my-experience-using-junie-for-the-past-few-months-38831.md>)

Original publisher: [Read original article](<https://lengrand.fr/my-experience-using-junie-for-the-past-few-months/>)

Author: Julien

Published: 2025-05-11T11:38:55Z

Content type: opinion

Language: en

Sources: [Thoughts, stories and ideas.](<https://devfeed.tech/sources/thoughts-stories-and-ideas.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [Programming](<https://devfeed.tech/topics/programming.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [coding](<https://devfeed.tech/tags/coding.md>), [development](<https://devfeed.tech/tags/development.md>), [experience](<https://devfeed.tech/tags/experience.md>), [intellij](<https://devfeed.tech/tags/intellij.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [junie](<https://devfeed.tech/tags/junie.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>)

### AI overview

A personal review of using JetBrains Junie over several months. The author describes Junie's Code and Ask modes, IntelliJ-based IDE integration, terminal command option, pricing, and distinctions from other JetBrains AI products. They value its IntelliJ integration, Kotlin support, and test-first focus, but criticize its slowness and limited ability to accept only part of a proposed solution.

### Source excerpt

Junie is one of the best coding agent I've been trying out so far. Very well integrated with IntelliJ, great for Kotlin, and the test first focus makes it quite good at coming out with good results. However, I do miss the capability to only accept part of a solution and it can be very slowwwwww.

## Does Junie Create Accessible Android Apps?

DevFeed: [Does Junie Create Accessible Android Apps?](<https://devfeed.tech/articles/does-junie-create-accessible-android-apps-38506.md>)

Original publisher: [Read original article](<https://eevis.codes/blog/2025-05-10/does-junie-create-accessible-android-apps/>)

Author: Eevis Panula

Published: 2025-06-10T04:54:16.242000Z

Content type: opinion

Language: en

Sources: [Eevis Blog](<https://devfeed.tech/sources/eevis-blog.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Web Accessibility (a11y)](<https://devfeed.tech/topics/web-accessibility.md>), [Android](<https://devfeed.tech/topics/android.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>)

Tags: [accessibility-testing](<https://devfeed.tech/tags/accessibility-testing.md>), [ai](<https://devfeed.tech/tags/ai.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [junie](<https://devfeed.tech/tags/junie.md>)

### AI overview

The article reports on two rounds of testing Junie, JetBrains' coding agent, by generating Android apps and evaluating their accessibility. It also discusses Junie's structured workflow, unnecessary library additions, a KSP version issue, and differences between its Early Access and generally available versions.

### Source excerpt

I'm continuing my tests with AI-generated Android code and how accessible these generated apps are. This time, the tool of choice is Junie, the coding agent by JetBrains. If you want to know why I'm doing this or want to read my take on how accessible code Gemini creates, the first post is available at Does Gemini Create Accessible Android Apps?. So, I got into the Early Access Program (EAP) before Junie was generally available and generated the first app. I had all these plans to proceed to the second run and write this blog post sooner, but then life happened, and I founded my own company. Suddenly, time passed, and Junie is now generally available. Before we dive into the application generation and accessibility testing, I'll share a couple of words about Junie I wrote right after the first try, with some additions after the second run. Junie As mentioned, I got access to EAP and was curious to try Junie out, as it differed from the AI solutions for coding I'd used before. Particularly, it also changed the files and didn't just give me the code, and I could skip all the hard work of creating files and copy-pasting the code into those files. Some thoughts I had: I was impressed by the structured approach for doing things. It was easy to follow what was happening next and what was coming after that. When creating the first app, Junie kind of went overboard with adding libraries like Room into the project, but not using them in the code. With the first app, I had to solve one KSP version issue by hand, because I got tired of Junie trying to find a working library version. It used some non-existent version numbers first. The second app used kapt, which resolved the version right away. I had to iterate a bit with the first version to get all the features I wanted, like adding yarn. The second app generation was smooth from this point of view. The App As with the tests with Gemini, I did two rounds of testing - first, with the Early Access Program version back at the b

## Vibecoding a Totoro tribute with Junie

DevFeed: [Vibecoding a Totoro tribute with Junie](<https://devfeed.tech/articles/vibecoding-a-totoro-tribute-with-junie-32084.md>)

Original publisher: [Read original article](<https://www.maiatoday.net/p/vibecoding-a-totoro-tribute-with-junie/>)

Published: 2025-03-02T21:02:23Z

Content type: tutorial

Language: en

Sources: [Maiatoday](<https://devfeed.tech/sources/maiatoday.md>)

Topics: [junie](<https://devfeed.tech/topics/junie.md>), [Jetpack Compose](<https://devfeed.tech/topics/jetpack-compose.md>), [Kotlin](<https://devfeed.tech/topics/kotlin.md>), [Canvas](<https://devfeed.tech/topics/canvas.md>), [shaders](<https://devfeed.tech/topics/shaders.md>)

Tags: [animate](<https://devfeed.tech/tags/animate.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [code](<https://devfeed.tech/tags/code.md>), [compose](<https://devfeed.tech/tags/compose.md>), [junie](<https://devfeed.tech/tags/junie.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>), [kotlin-multiplatform](<https://devfeed.tech/tags/kotlin-multiplatform.md>), [screen](<https://devfeed.tech/tags/screen.md>), [shaders](<https://devfeed.tech/tags/shaders.md>)

### AI overview

The article describes using Junie to experiment with visual drawing techniques in a Kotlin Multiplatform Compose desktop project. The project combines canvases, gradients, paths, shapes, text, shaders, animations, and interaction to create a Totoro tribute, without aiming for production readiness.

### Source excerpt

Sunday afternoon. Perfect time to hang out with Junie. I want to refresh my memory on some Compose drawing techniques. I am not really in the mood for Googling. I don't need a production ready app. I really just want to mess around. How far can I vibe code this. I'll start off by setting Junie to brave mode. I added an image and some colours to the repo of a blank compose desktop project. I also put a copy of an older blogpost of mine with some drawing techniques. I set some ground rules with the first prompt and then just keep asking Junie to add things. Create a guidelines file with the following information and update the README.md file. Let's explore some visual techniques in this Kotlin multiplatform project. The aim is to go for variety of techniques. Feel free to use the canvas, brush, paint, gradient, lines, paths, rounded polygons, skia shaders, text, colours, shapes. Or anything that will create an interesting visual effect. Animations are not necessary but can be added. The project does not have a practical application other than to demonstrate how to create interesting visual elements and to have some fun. It is a visual tribute to the Studio Ghibli film, [My Neighbor Totoro](https://en.wikipedia.org/wiki/My_Neighbor_Totoro). * It does not need any tests * Layer all the visual techniques on the main composable screen. * Find the suggested fonts in the resources folder * Find inspiration in the docs/looks folder and in the docs/blogpost folder I think Junie got what I wanted to do, I never explained what Totoro looks like but it figured out something from the included inspiration image. The early experiments needed some tweaking The only time the project didn't run was when Junie didn't download the new fonts but I found the instructions on where to get the fonts added to the README.md. I had no real expectations so I'm pretty happy with the final result. Animating rain and clickable wobbling Totoro. No explanations really what can I say I didn't read the