█

AI/TLDR

Continue

Open-source coding agent for your terminal, VS Code, and JetBrains, with AI checks you can put in CI

github.com/continuedev/continue★ 34.1kdocs.continue.dev

Overview

Continue is an open-source coding agent built by Continue Dev, Inc. and released under the Apache 2.0 license. You can use it three ways: a command-line tool called cn, a VS Code extension, and a JetBrains plugin. The agent works alongside you in your editor or terminal to help write, edit, and review code.

A core idea in Continue is moving AI review into your repository. Each check is a markdown file kept under version control next to your code. On every pull request, those checks run and show up as GitHub status checks, passing when the code meets your standards and failing with suggested fixes when it does not, so the rules are enforceable in CI.

Note: the continuedev/continue repository has reached a final 2.0.0 release and is now read-only and no longer actively maintained, but the code and the open-source CLI remain available for use and as a foundation for others.

What it does

  • Runs as a CLI (cn), a VS Code extension, and a JetBrains plugin from one project
  • Interactive terminal session, plus a headless mode for one-off prompts and automation
  • AI review checks stored as markdown files in your repo, kept under version control
  • Checks run on every pull request and appear as GitHub status checks (pass or fail)
  • Tool-permission flags let you allow, prompt before, or exclude specific agent tools
  • Apache 2.0 licensed and open source, so you can self-host and adapt it

Getting started

Install the Continue CLI, then start an interactive session or run a single prompt in headless mode. The CLI binary is named cn.

Install the CLI

On macOS or Linux, install the Continue CLI with the official install script.

bashbash
curl -fsSL https://raw.githubusercontent.com/continuedev/continue/main/extensions/cli/scripts/install.sh | bash

Start an interactive session

Run the cn command in your project to open an interactive coding session in the terminal.

bashbash
cn

Run a single prompt (headless)

Use the -p flag to run one prompt without the interactive UI, which is useful for scripts and automation.

bashbash
cn -p "your prompt here"

Use VS Code or JetBrains instead

Prefer an editor? Install the Continue extension from the VS Code Marketplace (or OpenVSX), or the JetBrains plugin. See docs.continue.dev for configuration.

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

When to use it

  • Pair with an AI coding agent in the terminal or your editor to write and edit code
  • Define AI code-review rules as markdown files in your repo and enforce them on every pull request
  • Run the CLI in headless mode inside CI pipelines to automate checks and prompts
  • Standardize team coding standards as version-controlled checks that show up as GitHub status checks

How Continue compares

Continue alongside other open-source autonomous coding agents tools AI/TLDR tracks, ranked by GitHub stars.

ToolStarsWhat it does
opencode★ 176kOpenCode is an open source AI coding agent that runs in your terminal, with built-in build and plan agents and an optional desktop app.
Gemini CLI★ 105kAn open-source command-line AI agent from Google that connects your terminal to Gemini models for reading code, editing files, running shell commands, and searching the web.
OpenHands★ 77.8kAn open-source AI software-development agent that plans tasks, edits files, runs commands, and tests code, usable from a terminal CLI, a local web GUI, or a Python SDK.
Goose★ 49.8kGoose is an open-source AI agent that runs on your machine for code, research, automation, and more, with a desktop app, CLI, and API built in Rust.
Continue★ 34.1kOpen-source coding agent for your terminal, VS Code, and JetBrains, with AI checks you can put in CI
Vibe Kanban★ 27.1kVibe Kanban lets you plan tasks on a kanban board, run coding agents like Claude Code and Codex in isolated workspaces, then review their diffs and ship pull requests.
Serena★ 25.6kSerena is an open-source MCP toolkit that gives any LLM coding agent symbol-level code retrieval, editing, and refactoring across 40+ languages.
Crush★ 25.5kCrush is a terminal coding agent from Charm. It connects your code, tools, and workflows to any OpenAI- or Anthropic-compatible LLM, with LSP context and MCP plugins.