For un assistant de codage IA pour IDE, the strongest matches are roovetgit/roo-code (Roo-Code is an AI-powered editor extension that acts as), zai-org/codegeex (CodeGeeX is an AI code completion engine and IDE-integrated) and shougo/deoplete.nvim (Deoplete). codota/tabnine and github/copilot.vim round out the shortlist. Each is ranked by relevance to your query, popularity and recent activity.
Nous sélectionnons les dépôts GitHub open-source correspondant à « ide ai assistants ». Les résultats sont classés par pertinence par rapport à votre recherche — utilisez les filtres ci-dessous pour affiner, ou utilisez l'IA.
Roo-Code is an editor extension and AI agent orchestrator designed to automate software engineering tasks. It functions as an LLM-powered tool that generates source code from natural language descriptions and manages autonomous agents directly within the development environment. The system distinguishes itself through the use of role-based behavioral profiles, allowing the agent to switch between personas such as Architect or Debugger to align with different project phases. It also operates as a Model Context Protocol client, connecting to external servers to expand the data sources and tools
Roo-Code is an AI-powered editor extension that acts as an agent orchestrator for automating software engineering tasks, directly integrating into IDEs to generate code from natural language, switch between personas for debugging or architecture, and connect to external tools — fitting the request for an AI coding assistant with refactoring, debugging, and context-aware support within the development environment.
CodeGeeX is a multilingual large language model and AI code completion engine designed to generate, translate, and complete source code across numerous programming languages. It functions as an intelligence layer that synthesizes logic from natural language prompts and existing code snippets. The project provides a specialized source code translator that converts logic and functionality between different programming languages while preserving the original behavior. It also operates as an integrated AI assistant suite, offering extensions that embed generative AI directly into development envi
CodeGeeX is an AI code completion engine and IDE-integrated assistant that generates, completes, and translates code across many languages — fitting your search for an AI-powered IDE coding assistant, though it doesn't mention a built-in chat interface or dedicated debugging support.
Deoplete.nvim is an asynchronous completion engine and framework for Neovim and Vim8. It functions as a non-blocking system for fetching and displaying text suggestions, serving as a modular extension that integrates multiple external completion sources without freezing the editor user interface. The project operates as a Language Server Protocol client, bridging the editor to external language servers to provide context-aware, type-safe completions. It further distinguishes itself by supporting intelligent text prediction through the integration of machine learning engines and language-speci
Deoplete.nvim is a code completion plugin for Neovim and Vim that supports Language Server Protocol and can integrate machine learning for intelligent suggestions, fitting the IDE assistant category but focused on completion rather than a full chat or debugging feature set.
TabNine is an AI-powered code completion engine that runs a deep-learning model to generate real-time code suggestions across all programming languages. It operates as an editor plugin that communicates with a backend through a JSON message-passing interface, processing code entirely on the local machine or within a private cloud to keep source code secure and private. The system provides a completion request API that accepts cursor context and returns ranked text completions, with features for configuring completion regions, prefetching files for indexing, and managing binary versions and up
Tabnine is an AI-powered code completion plugin that integrates into editors like VS Code, JetBrains, and Vim, offering real-time multi-language suggestions directly in the IDE, which aligns with the core intent, though it focuses on autocompletion and lacks the chat interface, full code generation, refactoring, and debugging features.
This project is a Vim plugin that functions as an AI-powered coding assistant. It integrates large language models directly into the text editor to provide real-time code suggestions and function completions based on the current file context and cursor position. The plugin distinguishes itself by utilizing an asynchronous event loop to maintain editor responsiveness while communicating with remote models. It employs a virtual buffer overlay to display generated code suggestions, allowing users to preview and accept proposed changes without modifying the underlying file until explicitly confir
This Vim plugin provides real-time AI-powered code completions and context-aware suggestions directly in the editor, matching the IDE integration and code assistance requirements, but it does not include a chat interface or explicit debugging/refactoring support.
CopilotForXcode is an AI-powered coding assistant integrated directly into Xcode as a source editor extension. It functions as an agent that can automate multi-step project tasks, such as editing files, running terminal commands, and searching across the entire codebase, all while understanding the full context of the current Xcode project. The assistant provides a context-aware chat interface that answers coding questions based on open files, symbols, and recent edits. It also offers diff-based code review, analyzing changes to provide feedback on code quality and potential issues before mer
This repository is an AI-powered coding assistant that integrates directly into Xcode as a source editor extension, providing context-aware chat, code completion, code review, and automated project tasks—exactly the kind of IDE plugin this search asks for, though it is limited to Apple ecosystem languages and does not explicitly include debugging support.
Cursor is an artificial intelligence-powered code editor built as a fork of the Visual Studio Code environment. It integrates machine learning models directly into the development workflow, allowing users to generate, refactor, and debug code through natural language prompts while maintaining full compatibility with existing editor extensions and themes. The editor distinguishes itself through a specialized codebase context engine that indexes local project structures and file relationships using vector-based embeddings. This system enables the editor to inject relevant file snippets and proj
Cursor is an AI-powered code editor that integrates natural language code generation, refactoring, and debugging directly into the development workflow, covering code autocompletion, chat, multi‑language support, and context‑aware suggestions in a single comprehensive assistant.
Tabby is a self-hosted AI coding assistant designed to provide real-time code completion and interactive chat capabilities within development environments. By functioning as a private server application, it allows teams to maintain control over their infrastructure and data while integrating intelligent code generation directly into their existing workflows. The platform distinguishes itself through its repository-aware knowledge retrieval and multi-model orchestration. It indexes local and remote source code repositories and technical documentation into a searchable vector-based knowledge gr
Tabby is a self-hosted AI coding assistant that integrates into IDEs for real-time code completion and interactive chat, but it does not explicitly emphasize debugging or refactoring support among its core features, making it a solid match for the core intent but not the most comprehensive example.
Trae-agent is an intelligent software development assistant designed to automate code generation, debugging, and task management within integrated development environments. It functions as an automated workflow orchestrator that monitors workspace changes and coordinates programming activities to streamline the software delivery lifecycle. The system utilizes large language models to synthesize source code while maintaining project integrity through structural tree manipulation and static analysis. By integrating with local development tools and monitoring file system events, it provides cont
Trae-agent is an AI-powered development assistant that integrates into IDEs to automate code generation and debugging, matching the core need for AI-driven coding help, though it focuses on autonomous workflow orchestration rather than interactive inline completions.