Back to directory

LM Local

A Visual Studio 2022/2026 extension that adds a local or cloud AI chat assistant with agentic capabilities, able to edit code, run builds and tests, and apply changes inside the IDE with tracked, reversible edits.

LM Local

LM Local is a Visual Studio extension that adds an AI chat assistant with agentic capabilities, working with local engines such as LM Studio, Ollama, Jan and Llama.cpp, as well as cloud providers including Groq, OpenRouter, Google AI Studio and DeepSeek through OpenAI-compatible APIs. Within a single conversational flow it can edit code, run builds and tests, and apply changes to the project.

By default its write and modify tools are disabled, so it can read files but not change anything until writing tools are explicitly turned on in settings; once enabled, every change is tracked in a Changes panel with one-click rollback. Its features include in-IDE chat with streaming responses, code autocompletion as the user types, image attachments for multimodal chat, expandable reasoning traces, custom system presets, chat history with session restore, and Model Context Protocol support for adding external tools over stdio or HTTP.

It requires Visual Studio 2022 or 2026, and its source is open for inspection and contribution on GitHub.

More in Editors

See all 109
  • QBasic Web Editor

    vahidyousefzadeh.com

    A browser-based QBasic 1.1 editor and interpreter that runs classic QBasic programs with DOSBox-accurate behavior, including text-mode graphics commands such as PRINT, COLOR and LOCATE, with sample programs and keyboard shortcuts to run and save.

  • Aliot SysML v2

    github.com

    A VS Code extension for editing SysML v2 and KerML systems-engineering models as text and diagrams, with validation, diagram views and CI-friendly automation.

  • Tycode

    tycode.dev

    An AI coding assistant that runs as both a command-line tool and a Visual Studio Code extension, using a bring-your-own-key model where the developer pays their configured AI provider - AWS Bedrock or OpenRouter - directly instead of a subscription.