Poolside Launches Free Open Model for Local Agentic Coding

American AI startup Poolside has released Laguna XS.2, a free, high-performing open-source model designed specifically for local agentic coding. The launch marks a significant step toward democratizing access to advanced AI-powered development tools. Unlike many coding assistants that rely on cloud-based servers, Laguna XS.2 can run entirely on a developer's local machine. This approach offers several advantages: enhanced privacy since code never leaves the device, reduced latency for real-time suggestions, and lower costs by eliminating cloud computing fees. Developers can also customize the model to their specific coding styles and project requirements. Poolside claims that Laguna XS.2 competes directly with proprietary models from Anthropic and OpenAI while being completely free and open-source. The model supports multiple programming languages and can handle complex agentic tasks, such as autonomously writing functions, debugging code, and even refactoring entire codebases. The release is part of a broader trend in the AI industry toward smaller, more efficient models that can run on consumer hardware. Laguna XS.2 is optimized for laptops and desktop computers with modest GPU requirements, making it accessible to individual developers and small teams who cannot afford expensive cloud subscriptions. Open-source advocates have praised Poolside's decision to release the model under a permissive license, which allows developers to modify, distribute, and build upon it without restrictions. This approach contrasts with the closed models offered by major tech companies, which often require paid subscriptions and limit how the technology can be used. Poolside's CEO stated that the company believes the future of AI-assisted coding lies in local, private, and customizable tools. By releasing Laguna XS.2 for free, Poolside hopes to accelerate innovation and give developers more control over their coding environments. The model is available for immediate download from the company's website and GitHub repository.