IntelliJ Idea Goes LSP: Java and Kotlin Intelligence Comes to VS Code, Cursor

7 hours ago

IntelliJ IDEA now offers its Java and Kotlin intelligence as an LSP server, available in a preview extension for VS Code and its forks like Cursor.
The extension provides smart code completion, navigation, analysis, refactorings, and support for Maven, Gradle, and Bazel.
During the preview phase, the extension is free to use with a 30-day evaluation period per build; after preview, an IntelliJ IDEA Ultimate subscription is required.
JetBrains is also working on supporting terminal-based agentic workflows, aiming to reduce token consumption and improve development efficiency.

Codapult provides a ready-to-use SaaS foundation with modules like auth, payments, teams, admin, AI, SSO, and infrastructure, allowing customization and scaling without rebuilding.
It includes full source code for flexibility, enabling changes to architecture, provider swaps, self-hosting, and avoiding vendor lock-in.
The stack is production-ready with folder structure, UI, payments, auth, docs, tests, deployment, and observability set up out of the box.

Sentinel is an open-source QA agent that reads the codebase to understand business flows and performs end-to-end testing across frontend and backend.
It autonomously derives critical business flows from the code, such as reservation lifecycle, group bookings, and payment processes, similar to a human QA engineer.
During testing, Sentinel interacts with both UI and API, catching backend bugs that UI-only tests miss, like state-machine inconsistencies and API/UI disagreements.

Brow6el is a full-featured terminal web browser using Chromium (CEF) with support for Sixel and Kitty graphics protocols.
The main repository has moved from Codeberg to a new location; Codeberg is kept for reference only.
It features Vim-style modal keyboard control with Standard, Insert, Visual, and Mouse modes.

Warp Agent is now available as a standalone CLI that works in any terminal (Ghostty, iTerm2, VS Code, Windows/Mac terminals).
The agent features built-in model routing with frontier and open-weight models, and supports custom model routers.
It supports advanced workflows like multi-agent orchestration and cloud agents, with automatic task delegation.

Gemini Distillation Service trains a smaller 'student' model using outputs and reasoning from a larger 'teacher' model.
It bridges the gap between frontier model capabilities and production efficiency, offering lower latency and cost.
Unlike supervised fine-tuning (SFT), distillation leverages both final responses and internal reasoning paths from the teacher.

Codapult provides a ready-to-use SaaS foundation with modules like auth, payments, teams, admin, AI, SSO, and infrastructure, allowing customization and scaling without rebuilding.
It includes full source code for flexibility, enabling changes to architecture, provider swaps, self-hosting, and avoiding vendor lock-in.
The stack is production-ready with folder structure, UI, payments, auth, docs, tests, deployment, and observability set up out of the box.

Sentinel is an open-source QA agent that reads the codebase to understand business flows and performs end-to-end testing across frontend and backend.
It autonomously derives critical business flows from the code, such as reservation lifecycle, group bookings, and payment processes, similar to a human QA engineer.
During testing, Sentinel interacts with both UI and API, catching backend bugs that UI-only tests miss, like state-machine inconsistencies and API/UI disagreements.

Brow6el is a full-featured terminal web browser using Chromium (CEF) with support for Sixel and Kitty graphics protocols.
The main repository has moved from Codeberg to a new location; Codeberg is kept for reference only.
It features Vim-style modal keyboard control with Standard, Insert, Visual, and Mouse modes.

Warp Agent is now available as a standalone CLI that works in any terminal (Ghostty, iTerm2, VS Code, Windows/Mac terminals).
The agent features built-in model routing with frontier and open-weight models, and supports custom model routers.
It supports advanced workflows like multi-agent orchestration and cloud agents, with automatic task delegation.

Gemini Distillation Service trains a smaller 'student' model using outputs and reasoning from a larger 'teacher' model.
It bridges the gap between frontier model capabilities and production efficiency, offering lower latency and cost.
Unlike supervised fine-tuning (SFT), distillation leverages both final responses and internal reasoning paths from the teacher.

Hasty Briefsbeta