AIAny
AI Client2025
Icon for item

vscode-copilot-chat

Source code for the GitHub Copilot Chat extension in VS Code: inline chat, an agent mode that plans and edits files autonomously, next-edit suggestions, and MCP integration. Open-sourced so developers can study how Copilot connects to an editor.

Introduction

Microsoft rarely ships the full source of a flagship commercial extension, yet here is the entire Copilot Chat codebase, archived in May 2026 once development folded back into the main VS Code repo. The real value is not the feature list everyone already knows; it's the chance to read how a production AI coding assistant is actually wired into an editor, prompt construction and all, rather than guessing from a demo.

What Sets It Apart
  • The agent loop is in the open: planning, file edits, command execution, and self-correction are coded as concrete TypeScript orchestration, not hidden behind a service boundary, so you can trace exactly how a task becomes a sequence of tool calls.
  • It is model-agnostic in practice. Beyond Copilot's own service models, the code shows how Claude and Codex providers are slotted in, which means the context-assembly logic is decoupled from any single LLM.
  • MCP server integration and custom instructions are first-class, so the extension doubles as a worked example of grounding an editor agent in external tools and project-specific rules.
Who It's For

Great fit if you are building an editor-integrated coding agent and want a real reference for prompt assembly, context gathering, and tool dispatch at production scale. Look elsewhere if you want something runnable or forkable: the repo is archived, active work moved to microsoft/vscode, releases shipped lockstep with the editor, and using the extension itself still requires a Copilot subscription. Treat it as a reading codebase, not a maintained dependency.

Information

  • Websitegithub.com
  • AuthorsMicrosoft
  • Published date2025/06/27

Categories

More Items

GitHub
AI Image2026

Node-based infinite-canvas web workstation for iterative visual creation — integrates image/video generation, reference editing, prompt library, multi-agent assistants, and asset management. Runs in-browser with configurable OpenAI-compatible endpoints; suited for local/personal deployment (AGPL-3.0).

GitHub
AI Client2026

Provides a deployable personal AI assistant that runs locally or in the cloud, supports multi-channel chat, extensible Skills/Plugins, and local-model runtimes. Key features include three-layer memory, kernel-level sandboxing and tool/file guards, and bundled QwenPaw-Flash local models for zero-API deployments.

GitHub

Provides a local-first web-intelligence layer for AI agents: search, fetch, crawl, extract, cache, find-similar and agent-style research without API keys or per-query billing, running as an MCP server, REST daemon, or SDK.