Explyt / Release archive
26 release notes since 28 Nov 2024. Latest: Explyt 5.19.
Explyt 5.19 opens subscription minutes to Claude Code, Cursor, Codex, Cline, OpenCode, and Kilo Code through an OpenAI-compatible gateway, fixes the context indicator, and renews MCP server tokens automatically.
Explyt 5.17 adds IDE-powered Move and Delete refactoring, a free MCP server for external agents, and chat branching.
Explyt 5.16 adds /btw for one-off questions in the context of an active task, strictness levels for repeating user rules, image handoff to multimodal subagents, IntelliJ Platform 2026.2 support, update notifications, and reliability fixes.
I'm the Explyt agent, and starting with version 5.15, I open with a short onboarding flow instead of a blank chat. From then on, in every chat I show you my token and minute usage the way top shows resource usage: live, right under the input box, no trip to settings required. One line tells you how many tokens I've already burned, how much context window I have left, and what the session has cost so far.
Explyt 5.14 adds Memory Bank for persistent project context, organized review reports, model routing profiles, and improved MCP support for everyday AI coding workflows.
Discover Explyt 5.13: improved test generation for WebStorm and PyCharm, better project context, external file access, onboarding, and faster AI coding workflows in JetBrains IDEs.
Explyt 5.12 adds a General AI agent, inline code attachments, Test mode for Rider, WebStorm, and PyCharm, cleaner AI code review, Simple chat mode, MCP improvements, and stability fixes for JetBrains IDE workflows.
This release is about the problems developers hit when AI starts doing real work inside the IDE: generated code can be unsafe, long chats can run out of context, MCP setups can overload the agent with tools, and test runs can fail because the agent guessed the wrong command. We worked on those parts. AI can write code fast. It can also write vulnerable code fast. Explyt 5.11 adds vulnerability search for JVM projects.
Explyt 5.10 makes the agent more integrated with your IDE workflow. It can now reuse Skills from dot directories used by other AI tools so that existing instructions can work across assistants, and show better hints for code and file links in chat, making it easier to view documentation or signatures without losing context. Explyt now searches for Skills not only in . explyt/skills//SKILL. md, but also in .
With Explyt 5.9, AIassisted development becomes more structured, more transparent, and more effective. The release introduces subagents for complex multistep tasks, expands builtin skills for planning and review, improves collaboration between the user and the agent, and adds usability updates that make everyday work in chat faster and clearer. The orchestrator agent can now invoke subagents — specialized agents for specific tasks such as coding, test generation, code review, and codebase research.
Debugging, running a project, and refactoring are core IDE capabilities that developers rely on every day. But until Explyt 5.8, even the most advanced AI coding agents could barely work with these essentials. With Explyt 5.8, we’ve made the agent much more deeply integrated with the IDE: it can now help with debugging, run configurations, and safe refactoring. On top of that, we’ve introduced several important workflow improvements and updated our pricing model.
Explyt 5.7 focuses on making everyday agent workflows smoother and more reliable. This release reduces friction in the moments that matter most: giving the agent broader project context, switching models more easily, recovering from temporary failures automatically, and staying focused while background commands run.
In Explyt 5.6, we improved the core user workflows that shape everyday work with the agent — making your user experience more convenient, transparent, and controllable.
In Explyt 5.5, working with the agent becomes more controllable, safer, and more extensible. SKILLs provide full support for an open skills standard: you can store them in your project, reuse them across tasks and tools, and the agent will automatically apply the right skills when needed. We also introduced new agent modes: Plan and Review.
The new Explyt 5.4 release focuses on practical improvements for everyday development. Personal users can now attach images directly in chat — especially useful for frontend work and UI testing. Requests to Anthropic models are now up to 70% cheaper thanks to improved caching, and large chats are automatically compressed without making additional LLM requests.
Explyt 5.3 introduces powerful updates for individual developers, including LLM selection in Settings for Personal plan users, new Agent modes, and UI improvements. Individual developers can now choose the LLM model they want to use with the agent. We have added three modes, and plan to implement more in the coming months.
We’re thrilled to share what’s new in Explyt 5.2. This release brings powerful updates for individual developers, including Anthropic now available in the Personal plan and official support for PhpStorm. Anthropic is now included in the Personal subscription, giving individual users access to advanced AI capabilities directly in Explyt. Explyt Agent capabilities are now available in PhpStorm.
We are pleased to share that DeepSeekV3.2 has been deployed in our VPC. This model sets a new quality benchmark for Explyt Enterprise. Based on the results of our internal benchmarks, it confidently outperforms Qwen3Coder480B in stability, depth of reasoning, and the ability to carry tasks through to real tangible results.
In Explyt 5.1 common workflows are now available straight from the new chat window! We have redesigned the interface to focus more on developer and tester scenarios. When you open a new chat, you will see a list of common tasks that Explyt can help you with. You can immediately jump into a particular scenario by clicking the run button to the left of it.
We are happy to introduce Explyt 5.0 with Rider support. Developing and testing C applications is now even more efficient with Explyt. Previously, when generating tests in Java/Kotlin projects, the Explyt plugin provided only a fixed set of settings (such as choosing the testing and mocking frameworks, and the type of tests). When fixing tests, it followed a rigid pipeline.
We’re excited to share some great news: Explyt is now available for download on JetBrains marketplace . Just oneclick install from your IDE. We encourage you to rate the plugin and share your honest feedback. New versions of the plugin may appear on the marketplace with a slight delay, so we’ve kept the option to install it from our website.
Just two weeks ago we annonced Explyt 4.1 with Python and MCP servers support, and today we are thrilled to share a new version Explyt 4.2 with Go support to boost your coding with GoLand. The cuttingedge features of Explyt agent are now available in GoLand. Starting with Explyt 4.2, we are introducing a new user registration procedure.
Explyt 4.1 introduces new powerful features for an even better coding, testing, and debugging experience.
Explyt 4.0 introduces cuttingedge Coding Agent and Test Generation from Execution features for an even better coding, testing, and debugging experience.
What's new in Explyt Test 3.1 Explyt Test 3.1 takes a significant step forward in delivering an even better test generation experience introducing revised prompts algorithms, incremental fixes that do not rewrite the whole test file, and GPT4.1 support.
Explyt Test 2.0 includes functionality introduced in the EAP release, and has been enhanced with a range of powerful updates: expanded test generation management features Explyt Chat AI assistant with an intuitive and userfriendly UX. It provides code explanations, error analysis, and supports attachments. compatibility with IntelliJ IDEA 2024.3 and K2 for IntelliJ IDEA 2024.2+ Have a great day!
What impressed me most is how well the agent understands the existing project. Its plans fit naturally into what is already built, even when I am working outside my usual tech stack.
Senior Analyst Developer · DXC Technology
LSP gives an agent coordinates; the full IDE gives it the project model. That native IDE context makes all the difference on real Java code.
Software Architect & AI Board Lead · Siemens
IDE-native stepping makes the difference on stateful Java applications.
Software Engineer
Explyt 5.19: your subscription in Claude Code, Cursor, Codex, and other tools
Frequently Asked Questions
