@ihtesham2005: GitHub Copilot charges $10/month. Cursor charges $20/month. And both of them send every line of your code to their serv…
Summary
Continue is an open-source AI coding assistant that integrates with VS Code and JetBrains, supporting multiple models (Claude, GPT-4o, DeepSeek, etc.) and offering chat, autocomplete, edit, and AI-powered pull request checks.
View Cached Full Text
Cached at: 05/08/26, 03:35 PM
GitHub Copilot charges $10/month. Cursor charges $20/month. And both of them send every line of your code to their servers. Someone open sourced the alternative and it now has 33K+ stars. It’s called Continue. Here’s what makes it different from everything else: You pick the model. Claude, GPT-4o, DeepSeek, Gemini, Llama, Mistral, any local model running in Ollama. Continue doesn’t care. It connects to whatever you want. Your code never leaves unless you send it to a model that already has your trust. And it lives inside VS Code and JetBrains. Same keyboard shortcuts. Same sidebar. Zero context switching. Here’s what it actually does: → Chat: highlight any code and ask questions without leaving your editor → Autocomplete: inline suggestions as you type, powered by whatever model you chose → Edit: rewrite a block of code in place without touching any other file → Actions: one-click shortcuts for the things you do every day review this function, write a test, explain this error The part that makes it worth switching: Continue just shipped AI checks that run on every pull request as GitHub status checks. You write the check as a markdown file. It runs on every PR diff. Green if it passes, red with a suggested fix if it doesn’t. Security review. Test coverage. Code style. Anything you can describe in plain English, you can enforce automatically. GitHub Copilot can’t do this. Cursor can’t do this. 33K stars. Apache 2.0. 100% Opensource. https://github.com/continuedev/continue… https://continue.dev
continuedev/continue
Source: https://github.com/continuedev/continue
Continue

Getting started
Paste this into your coding agent of choice:
Help me write checks for this codebase: https://continue.dev/walkthrough
How it works
Continue runs agents on every pull request as GitHub status checks. Each agent is a markdown file in your repo at .continue/checks/. Green if the code looks good, red with a suggested diff if not. Here is an example that performs a security review:
---
name: Security Review
description: Review PR for basic security vulnerabilities
---
Review this PR and check that:
- No secrets or API keys are hardcoded
- All new API endpoints have input validation
- Error responses use the standard error format
Install CLI
AI checks are powered by the open-source Continue CLI (cn).
macOS / Linux:
curl -fsSL https://raw.githubusercontent.com/continuedev/continue/main/extensions/cli/scripts/install.sh | bash
Windows (PowerShell):
irm https://raw.githubusercontent.com/continuedev/continue/main/extensions/cli/scripts/install.ps1 | iex
Or with npm (requires Node.js 20+):
npm i -g @continuedev/cli
Then run:
cn
Looking for the VS Code extension? See here.
Contributing
Read the contributing guide, and join the GitHub Discussions.
License
Similar Articles
GitHub Copilot App
GitHub Copilot is an AI-powered code completion tool that assists developers by suggesting code snippets and functions in real-time.
Improving token efficiency for GitHub Copilot in VS Code
The VS Code team details recent optimizations to GitHub Copilot's agentic harness, such as prompt caching and tool search, to improve token efficiency and reduce costs under usage-based billing.
AI costs how much? GitHub Copilot users react to new usage-based pricing system.
GitHub Copilot's new usage-based pricing model causes sticker shock among users, with some burning through a month's credits within a day. The change ends the previous subsidy model that kept costs low for heavy users.
VS Code's new "Agents window" lets you use local AI models. Still requires an Internet connection and a Github Copilot plan (because we can't have nice things)
VS Code's new 'Agents window' allows developers to use local AI models, but still requires an Internet connection and a GitHub Copilot subscription.
A reckoning is coming for US AI coding tools
GitHub Copilot has switched to usage-based billing, making the cost of AI coding agents visible and signaling the end of the subsidized era for US AI coding tools. This shift may reduce US market share as developers realize they don't need expensive frontier models for most tasks.