Extensions

Aperture for Copilot Chat

he0119

Expose OpenAI-compatible Aperture models inside the GitHub Copilot Chat model picker.

Cabin Kit

Uchiha-Labs

Assemble, compress, and copy multi-file AI context with a live token budget. No API keys. Runs entirely in VS Code.

Learn While Coding

Devps2003

Learning cards for Cursor Agent, Claude Code, and Copilot — install and go

Badgr Auto — Token Optimization, Smart Routing, Local Models & Receipts

aibadgr

Cut AI coding costs with token optimization — strip repeated context on every request. Then route across local models, cheaper cloud tiers, and premium fallbacks. Track savings, latency, and receipts in VS Code.

TokGuess

maazizit

Track Copilot, Claude & Antigravity CLI tokens + Context Budget alerts before you send. Dashboard, optional local OTel precision mode (auth-protected, localhost-only), zero cloud.

React Graph AI — Token-Slim AI Context for React

react-graph-ai

Prune your React/Next.js codebase to minimal AI context. Reduces LLM token usage by 90%+ for GitHub Copilot, Claude, ChatGPT, and any AI tool.

Compress your Copilot Chat prompts and command output to save tokens — meaning-preserving, code-safe, no model call.

ChatLens — Copilot Chat History Search

PrashantVerma

Search, browse, and re-read your entire VS Code Copilot chat history. Local, read-only, offline.

Babs - open-source AI code agent forked from Continue

BasseyA

The leading open-source AI code agent

SavicLabs — Local AI for Copilot

SavicLabs

Use your local llama.cpp models in GitHub Copilot Chat. Zero config — auto-discovers models, supports thinking/reasoning, tool calling, and vision proxy.

W.A.R.A.N

waran

A VS Code extension for local AI-powered software development using Ollama, LM Studio, llama.cpp, and LocalAI.

Buddy AI Coding Agent

ishankrs

AI coding agent for VS Code — chat with @buddy, edit files, run terminal, search the web. Multi-provider LLM (OpenAI, Anthropic, OpenRouter, Ollama).