GitHub Copilot alternatives in 2026: 8 editors and agents to use instead

Disclosure: Enjoy is our product. We checked every app below against its maker’s own pages on October 29, 2026, and we say where another app is the better pick, Copilot included.

GitHub Copilot alternatives compared

GitHub Copilot began as code suggestions as you type. It now has chat, an agent mode, a command line, the Copilot app and agents that work in GitHub’s cloud, and its feature matrix covers VS Code, Visual Studio, JetBrains IDEs, Eclipse and Xcode, with code completion in Neovim too. Some of the apps people weigh against it are editors that suggest code as you type; others are agents you hand a task to. Several work together.

App	Best for	Price, checked October 29, 2026	Works in	Models
GitHub Copilot	Suggestions and an agent in almost any IDE	Free; Pro $10 a month; Pro+ $39; Max $100; Business $19 a seat	VS Code, Visual Studio, JetBrains IDEs, Eclipse, Xcode; a CLI and the Copilot app	Claude, GPT, Gemini, Grok and Kimi; Opus 5.5, GPT-6.1 Sol and Gemini 4 Argon from Pro+
Devin Desktop, formerly Windsurf	The closest AI editor, with quotas that refresh daily and weekly	Free; Pro $20 a month; Max $200	Mac, Windows, Linux; Windsurf for JetBrains	OpenAI, Claude, Gemini and SpaceXAI models from Pro
Cursor	An AI editor, with Grok included	Free; Plus $8 a month, Cursor’s own models only; Premium $30, other labs’ models at API prices	Mac, Windows, Linux	Grok and Composer; Claude, GPT-5.6 and Gemini billed separately
JetBrains AI	Staying in IntelliJ IDEA, PyCharm and the other JetBrains IDEs	AI Free; AI Pro $100 a year; AI Ultimate $300 a year	JetBrains IDEs	OpenAI, Anthropic, Google and xAI models; Junie, Claude Agent and Codex
Zed	An open-source editor, with your own keys, agents or Copilot	Free with your own keys or agents; Pro $10 a month	Mac, Windows, Linux	Any provider’s key, or Claude, Codex and other agents
Cline	An open-source agent in your editor, with your own keys	Free; ClinePass $9.99 a month, for open-weight models	VS Code and editors built on it, JetBrains IDEs, a CLI	Any provider’s key
Claude Code	Claude, on your Claude plan, in VS Code or a JetBrains IDE	Claude Pro $20 a month, or $17 billed yearly; Max from $100	VS Code, Cursor and other forks, JetBrains IDEs; a terminal and the Claude app	Anthropic’s Claude models
Codex	GPT, on your ChatGPT plan, with a free start	Free and Go in the desktop app; Plus $20 a month; Pro from $100	VS Code and its forks, JetBrains IDEs, Xcode; the ChatGPT app	GPT-6 Luna on Free and Go; GPT-6.1 Sol from Plus
Enjoy	Several labs’ agents side by side, on your own plans	A monthly subscription, free for 7 days, with your phone and other computers (pricing)	Mac, Windows, Linux	Claude Code, Codex, Grok Build, Antigravity, Muse Code, OpenCode

Prices are per month as each maker lists them in the US, before tax, unless the maker sells by the year. Copilot, Devin Desktop, Cursor, JetBrains AI and Zed Pro sell their own AI usage; Claude Code and Codex come with Anthropic’s and OpenAI’s plans; and Zed’s free plan, Cline and Enjoy run on the keys, agents and plans you bring.

Why people look for a Copilot alternative

Three things on GitHub’s own pages send people looking:

• Chat and agents now bill by the token. “As of June 1, all Copilot plans bill based on GitHub AI Credits consumed,” says GitHub’s changelog. A credit is a cent, and what a request costs depends on the model and the number of tokens: “A long Copilot cloud agent session using a frontier model across multiple files will cost more AI credits,” per its billing guide. Pro’s 1,500 credits a month are 1,000 base credits and a 500-credit flex allotment, which “is designed to adapt as the economics of AI evolve.”
• A month’s credits are all you get, unless you pay. “Included AI credits do not carry over between months,” and the allowance resets “at 00:00:00 UTC on the first day of each calendar month.” Until then, you upgrade, wait, or “continue working by setting a budget for additional usage,” though “additional usage may be capped.”
• The top models need Pro+. GitHub’s plans page marks Claude Opus 5.5, GPT-6.1 Sol and Gemini 4 Argon “Not included” on Pro, and “On Copilot Free and Copilot Student plans, access to models is available through auto model selection only.”

The cloud agent’s sandboxes cost money too, from November: “Billing for cloud sandbox usage begins in November 2026,” says GitHub’s Universe changelog. Sandbox time draws on the compute your GitHub plan includes, which Actions runners in private repositories share: $12 a month on GitHub Free, per its plan allowances. Our memo on Universe has the details.

Devin Desktop, formerly Windsurf

Best for: an AI editor close to VS Code with Copilot, with quotas that refresh daily and weekly instead of credits by the month.

“Devin Desktop is the new name for Windsurf,” says its page, and “Only the name and branding are changing.” It’s an AI editor with “Unlimited Tab completions” on every plan, an “Agent Command Center (Spaces, Kanban view, and multi-agent management),” and Devin Local, “Our next-generation agent harness, shared with Devin CLI.” Its docs cover Mac, Windows and Linux and say you can “Import VS Code or Cursor settings.” For JetBrains users, “Windsurf for JetBrains (IntelliJ IDEA, PyCharm, WebStorm, and more) continues to be available for download.”

Price: its pricing has Free, with a “Light quota to code with agents” and “Limited model availability”; Pro at $20 a month, with “Increased quotas, including access to frontier models from OpenAI, Claude, Gemini, and SpaceXAI”; and Max at $200, with “Significantly higher quotas.” Teams is $80 a month for the team plus $40 for each full developer seat.

Watch for: its pricing page doesn’t put a number on the quotas. “Each paid plan comes with a usage allowance that refreshes automatically on a daily and weekly basis,” and past it, “you can purchase extra usage which is consumed at API pricing.”

Cursor

Best for: an AI code editor with Grok’s models included, if you don’t need other labs’ models in the plan.

Cursor is an AI code editor, and “The Cursor desktop app is available for macOS, Windows, and Linux,” per its downloads. “Cursor is sold as part of The X Subscription, one subscription for Grok, Cursor, and X,” says its models page, and its paid plans’ pool of usage “refreshes weekly, so one heavy day doesn’t use up your month.”

Price: its pricing has Free, with “Limited agent requests”; Plus at $8 a month; Premium at $30, with “4x more usage compared to Plus”; Super at $100; and Ultra at $200.

Watch for: “Plus and Free don’t include third-party models,” and Plus has “No Auto, Cloud Agents, Automations, Bugbot, Origin, third-party models, or your own API keys.” On Premium and above, Claude, GPT and Gemini are paid “at the model’s API list price from the first request,” and its list has OpenAI’s GPT-5.6 models, not GPT-6. Our Cursor alternatives guide covers its plans.

JetBrains AI

Best for: staying in IntelliJ IDEA, PyCharm and the other JetBrains IDEs, with JetBrains’ own agent or the ones you already pay for.

JetBrains AI “provides access to AI models from leading providers such as OpenAI, Anthropic, Google Gemini, and xAI, as well as JetBrains’ own model for code completion,” says its pricing page, and it powers JetBrains Air, “giving you access to coding agents like Codex, Claude Agent, Gemini CLI, and Junie by JetBrains.” Junie is “JetBrains’ own cost-efficient coding agent.” In the IDEs, Air “works with any agent you already use,” and you can “Bring your existing provider subscriptions or API keys”: “Run Claude Code using your Claude subscription in Air’s terminal and full-screen IDE tab.”

Price: AI Free costs nothing, with “Unlimited AI completion in JetBrains IDEs” and three AI credits every 30 days; AI Pro is $100 a user a year, with 10 credits a month and a free 30-day trial; and AI Ultimate is $300 a year, with 35. “One AI credit equals USD 1.00 of AI use,” and “Usage of third-party AI models is billed at public API rates, with no surcharge.”

Watch for: the credits are dollars of API use, and “Unused credits don’t roll over.” AI Free “isn’t available in IntelliJ IDEA without Ultimate subscription and in PyCharm without Pro subscription, and Android Studio,” and JetBrains says “Prices shown are approximate.” Air adds that “a JetBrains AI subscription is currently required for cloud runs.”

Zed

Best for: an open-source editor that’s free with your own API keys, with agents such as Claude Code and Codex, or with your Copilot plan.

Zed is a code editor for macOS, Windows and Linux, per its downloads, with its code on GitHub: “Since Zed is open source,” its pricing page says, its admin controls govern only its hosted services. Its own agent works with your provider’s key, and it runs other agents in the editor: its docs list Claude, Codex, OpenCode and Copilot, and “Zed does not charge for External Agents.” Its edit predictions, suggestions of your next edit as you type, come from Zed’s own model on Pro, and on the free plan “you can use other providers, like GitHub Copilot.”

Price: its pricing has Personal at $0, “Free forever,” with “Unlimited use with your API keys or external agents like Claude Agent, Codex CLI, and more.” Pro, at $10 a month, adds “Unlimited edit predictions” and “$5 of tokens included,” and beyond that, “Zed Pro bills at API list price +10% for hosted usage.” Business is $30 a seat.

Watch for: on the free plan, the AI is whatever you bring. External agents “run through their own process and provider relationship,” and “Billing, legal terms, retention, and data handling are between you and the agent provider,” so Claude Code still needs a Claude plan. Zed is its own editor, so you set it up anew.

Cline

Best for: an open-source agent inside the editor you already use, with your own API keys and no subscription.

“Cline is an AI coding agent that lives in your editor and your terminal,” say its docs, and “Every action requires your explicit approval.” It comes as a VS Code extension, a CLI and a JetBrains plugin, “The same Cline experience in IntelliJ IDEA, PyCharm, WebStorm, GoLand, and the rest of the JetBrains family,” and it’s open source under Apache 2.0 on GitHub.

Price: “The Cline open source extension is completely free for individual developers,” says its pricing. “You only pay for AI inference on a usage basis,” and “You can bring your own API keys from providers like OpenAI, Anthropic, Google, and others.” ClinePass, at $9.99 a month, “is a low-cost subscription that includes open weight models in Cline,” from Z.ai, Moonshot AI, DeepSeek, MiniMax, MiMo and Qwen.

Watch for: you pay for the models separately, and an Anthropic or OpenAI key bills by the token, apart from any Claude or ChatGPT plan you pay for. Its pricing page lists the VS Code extension and the CLI on its free plan and puts “JetBrains Extension” under Enterprise, so check what you get in a JetBrains IDE before you count on it.

Claude Code, in VS Code and JetBrains IDEs

Best for: Claude, on the Claude plan you pay for, in the editor you already use.

Claude Code is Anthropic’s coding agent: you hand it a task, and it reads your project, edits files and runs commands. Its VS Code extension “provides a native graphical interface for Claude Code, integrated directly into your IDE,” installs in VS Code 1.94.0 or later and in Cursor, and “also installs in forks like Devin Desktop or Kiro.” In JetBrains IDEs, its plugin “runs the claude command in your IDE’s integrated terminal” and opens Claude’s changes in the IDE’s diff viewer. Anthropic’s help center says “Your Pro or Max plan also covers Claude Code in supported IDEs, including VS Code, Cursor and other VS Code forks, and JetBrains IDEs like IntelliJ and PyCharm.”

Price: “Claude Code is included in all paid plans,” says Claude’s pricing: Pro at $20 a month, or $17 a month billed yearly, and Max from $100. “The free claude.ai plan does not include Claude Code access,” per its setup guide.

Watch for: it runs only Claude, and “Both Pro and Max plans have a five-hour session limit and a weekly limit,” which “are shared across Claude and Claude Code.” In the editor, “Some features are only available in the CLI.” Our Claude Code vs Codex guide compares it with OpenAI’s agent.

Codex, in your editor and the ChatGPT app

Best for: GPT on the ChatGPT plan you pay for, with a free way to start.

OpenAI’s Codex runs in the ChatGPT desktop app, in a terminal and in your editor. Its IDE guide says “VS Code and compatible editors use the Codex extension; Xcode and JetBrains IDEs provide their own integrations”: in a JetBrains IDE, “open AI Chat and select Codex.”

Price: Codex’s pricing gives Free and Go “GPT-6 Luna at Standard speed in the desktop app, subject to rollout.” Plus adds “Codex on the web, in the CLI, in the IDE extension, and on iOS” and GPT-6.1 Sol, at $20 a month, per OpenAI’s help center, and Pro is $100, $200 or $500 a month.

Watch for: Codex in your editor starts with Plus, since the free plans get only the desktop app. OpenAI estimates 15 to 160 local messages every five hours with GPT-6.1 Sol on Plus, but “These estimates are not fixed message limits,” and “Weekly limits may also apply.” “ChatGPT Work and Codex share usage,” and it runs only OpenAI’s models.

Enjoy

Best for: handing tasks to Claude Code, Codex and other labs’ agents side by side, on the plans you already pay for, when you’d rather describe a change than type it.

Enjoy is a desktop app for Mac, Windows and Linux that runs Claude Code, Codex, Grok Build, Antigravity, Muse Code, and local models through OpenCode, on the plans you already have: most sign in with their own lab’s account, and OpenCode uses the providers you set up in it; its homepage says you can “Log in with GitHub to use your Copilot account.” What it adds:

• Switch agents mid-conversation. Hand a job from Codex to Claude Code or Grok Build: “The new agent gets the conversation so far, including replies from other agents, before it works on your message.”
• Keep going through limits. Claude’s and ChatGPT’s plans reset their limits within hours or a week, not once a month. When an agent runs out, Enjoy switches to another of your accounts or waits for the reset, then carries on.
• Your files, on your computer. Agents run “on your computer, inside your project’s folder,” so the editor you keep open shows each change. In Enjoy, View changes shows what each commit changed, line by line, and you can edit your project’s files in its code editor.
• Every project at once. Each conversation runs its own agent, and JOY keeps an eye on all your projects: ask it what needs you, or start work in any of them.

Price: Enjoy is one monthly subscription, and the first seven days are free, with a card to start. It includes your phone and any browser and your other computers, and each teammate you invite needs a subscription of their own. See pricing. The agents are billed separately: Claude Code needs a paid Claude plan and Codex in Enjoy needs ChatGPT Plus or above, while Antigravity works with a free Google account and OpenCode with free or local models.

Watch for: Enjoy isn’t an editor in Copilot’s sense. Its code editor has no AI completions as you type, and it doesn’t plug into VS Code or JetBrains IDEs: the agents write the code. It doesn’t add Claude to a ChatGPT plan or GPT to a Claude one, and it runs the Codex CLI, which OpenAI includes from Plus. Enjoy isn’t open source, it’s a monthly subscription on top of your AI plans once the free week ends, and scheduled workflows run only while your computer is awake with Enjoy open.

When to stay with Copilot

If you want suggestions as you type in whatever IDE you use, Copilot is hard to beat on reach. Pro, at $10 a month, includes Claude Sonnet 5.5, GPT-6.1 Terra and Gemini 3.8 Flash, and GitHub says “Code completions and next edit suggestions are not billed in AI credits and remain unlimited for all paid plans.” If a month runs short, “The upgrade cost is only the price difference between your current plan and the new plan.”

You don’t have to leave it to use the labs’ own agents, either. GitHub’s docs say Copilot runs Anthropic’s Claude and OpenAI’s Codex as third-party agents that “can be powered by your existing Copilot subscription,” in public preview; its pricing page lists them from Pro+, though its docs include Pro. Codex’s agent there offers GPT-5.3-Codex and GPT-5.4 nano, not the GPT-6 models. And Claude Code’s and Codex’s own extensions install in VS Code beside Copilot.

Move when the monthly credits are what stop you, when you want Opus 5.5 or GPT-6.1 Sol without Pro+, or when you’d rather use a Claude or ChatGPT plan you already pay for.

How we compared

We read each maker’s homepage, pricing, plans and docs, and Cline’s and Zed’s GitHub repositories, on October 29, 2026, and every one is linked below. We quote their own words for the limits, and we don’t count features a maker hasn’t documented. Two names many lists still recommend aren’t here. Google says “Starting June 18, 2026, Gemini Code Assist IDE extensions stopped serving requests” for individual accounts, and AWS says “On April 30, 2027, AWS will discontinue support for Amazon Q Developer IDE plugins,” pointing to Kiro, which our Cursor alternatives guide covers. Plans and credits in this category change often, so we recheck this guide against its sources at least once a month, and the date at the foot of the page says when we last did.