Tag
Hasan Toor argues that Cursor is no longer the best option for developers because it wastes tokens reconstructing a semantic model that JetBrains IDEs already index, suggesting a new agent that reads the index directly.
JetBrains benchmarked the Caveman token-compression skill on Claude Code across 86 tasks, finding real output-token savings of about 8.5% (not the advertised 65%) with no detectable degradation in task quality.
Marimo announces a plugin for PyCharm and JetBrains IDEs, allowing users to run reactive notebooks alongside their Python code with automatic module reloading and sandbox mode.
JetBrains has open-sourced YouTrackDB, a general-use object-oriented graph database with features like O(1) link traversal, snapshot isolation, TinkerPop/Gremlin support, and a custom SQL-based query language YQL. It is used internally in production and is available under Apache 2.0.
The article discusses how JetBrains is quietly building an AI ecosystem for developers with tools like AI Assistant, their own coding model Mellum, and open-source AI projects, potentially positioning itself as a major AI winner.
JetBrains launches Mellum, a fast LLM designed for low-latency and high-performance workflows.
Kotlin 2.4.0 is released with stable context parameters, explicit backing fields, improved multiplatform support including Swift packages as dependencies, and compatibility with Java 26 and Gradle 9.5.0.
JetBrains introduces Mellum2, a 12B parameter Mixture-of-Experts model optimized for code generation and reasoning tasks, with a focus on private deployment and integration into development workflows.
JetBrains open-sources Mellum2, a fast 12B Mixture-of-Experts model designed for low-latency AI workflows in software engineering, available under Apache 2.0 license.
JetBrains released Mellum 2 12B A2.5B, a coding-focused small MoE model with reasoning performance comparable to Qwen 3.5 9B but weaker in other tasks.
JetBrains releases Mellum2-12B-A2.5B-Thinking, an open-source Mixture-of-Experts reasoning model with 131k context length, trained with RLVR for explicit chain-of-thought reasoning.
JetBrains launched 'Air', a new development environment specifically designed for orchestrating multiple AI coding agents in parallel to handle complex tasks simultaneously without interference.
JetBrains, a major IDE provider used by 15M developers globally, is integrating OpenAI models including GPT-5 into its development tools through products like Junie (coding agent) and AI Assistant, focusing on enhancing developer workflows while maintaining code quality and engineering excellence.
JetBrains has launched an AI Assistant that integrates OpenAI's API into its IDEs, extending the company's existing intelligent code completion and inspection features with generative AI capabilities for enhanced developer productivity.
Kilo Code is an open-source AI coding agent that integrates with VS Code, JetBrains, and the CLI, offering access to 500+ models at provider pricing with no markup.