Updated

GitHub Copilot alternatives

Of the 657 products launched in 2026 that we know the AI coding agents of, 2% use GitHub Copilot, against 9% of those launched in 2023 or earlier. The most picked now is Claude Code (84%, up from 82%). On GitHub, 66 public pull requests since Oct 2024 moved projects off GitHub Copilot: Claude Code (40), OpenAI Codex (14), Cursor (7) and OpenCode (5); 57 moved to GitHub Copilot.

12 of the 19 are open source or self-hostable (OpenAI Codex, OpenCode, Pi and 9 more) and 9 have a free tier. For a team of 5 with 10,000 users, the cheapest is OpenAI Codex at $40 a month on ChatGPT Go, against $50 for GitHub Copilot on Pro. GitHub Copilot also answers AI code editors and AI code review: those alternatives are below too.

12 open source or self-hostable9 with a free tier5 ready for AI agents

Not a ranking: each option is described by the situation it fits, with its trade-off.

What new products use instead

The share of makers' products we track that use each for AI coding agents, by the year they launched on Product Hunt. The stack is the one we see today, not the one it launched with; a product can use more than one.

OptionLaunched ≤2023 · 34Launched 2025 · 126Launched 2026 · 657
Claude Code82%88%84%
OpenAI Codex9%6%19%
OpenCode9%3%5%
GitHub Copilot9%9%2%
Aider0%1%0%

Where projects leaving GitHub Copilot went

Public pull requests on GitHub since Oct 2024 whose title says "GitHub Copilot to …" or "… to GitHub Copilot": real code changes, by developers in general, not only makers. Each count opens the search that finds them.

ToolMoved from GitHub CopilotMoved to GitHub Copilot
Claude Code4028How they moved →
OpenAI Codex1422
Cursor70
OpenCode57

GitHub Copilot alternatives compared for AI coding agents

How many makers' products we track use each for AI coding agents, and what each costs for a team of 5 with 10,000 users.

OptionKindMakers' productsTeam of 5, 10,000 usersFree tierOpen source
GitHub CopilotCloud agent27$50/mo · ProYesNo
Claude CodeTerminal agent772$100/mo · ProNoNoCompare →
OpenAI CodexTerminal agent145$40/mo · ChatGPT GoYesYesCompare →
OpenCodeTerminal agent44$50/mo · GoYesYes
PiTerminal agent4—YesYes
Gemini CLITerminal agent0—YesYes
gooseTerminal agent0—YesYes
AiderTerminal agent1—YesYes
AmpTerminal agent0——No
DevinCloud agent0——No
JulesCloud agent0——No
FactoryCloud agent0——No
OpenHandsCloud agent0—YesYes
Kimi CodeTerminal agent0—NoYes
Mistral Vibe CLITerminal agent0——Yes
Grok BuildTerminal agent0——Yes
CrushTerminal agent0—YesNo
Qwen CodeTerminal agent0——Yes
Oh My PiTerminal agent0—YesYes
CodegenCloud agent0——No

GitHub Copilot alternatives compared for AI code editors

How many makers' products we track use each for AI code editors, and what each costs for a team of 5 with 10,000 users.

OptionKindMakers' productsTeam of 5, 10,000 usersFree tierOpen source
GitHub CopilotEditor plugin0—YesNo
CursorAI-first editor542$40/mo · PlusYesNoCompare →
Devin Desktop (formerly Windsurf)AI-first editor37$100/mo · ProYesNoCompare →
ZedAI-first editor32$50/mo · ProYesYes
Google AntigravityAI-first editor13—YesNo
KiroAI-first editor6$100/mo · ProYesNo
ClineEditor plugin3—YesYes
JetBrains JunieEditor plugin0—YesNo
Kilo CodeEditor plugin11—YesYes
TraeAI-first editor8—YesNo
Augment CodeEditor plugin7—NoNo
ContinueEditor plugin5—YesYes
ZencoderEditor plugin1—NoNo
Claude CodeEditor plugin0—NoNoCompare →
OpenAI CodexEditor plugin0—YesYesCompare →
QoderAI-first editor0—YesNo
TabnineEditor plugin0——Self-hostable
Roo CodeEditor plugin0——Yes
Blackbox AIEditor plugin0——No
SupermavenEditor plugin0——No
Sourcegraph CodyEditor plugin0——No
Sweep AIEditor plugin0——No
Amazon Q DeveloperEditor plugin0——No

GitHub Copilot alternatives compared for AI code review

How many makers' products we track use each for AI code review.

OptionKindMakers' productsFree tierOpen source
GitHub CopilotBundled with your assistant0YesNo
GraphiteReview platform13—No
CodeRabbitDedicated AI reviewer9—No
cubicDedicated AI reviewer9—No
GreptileDedicated AI reviewer1—Self-hostable
PR-AgentOpen-source, self-run0—Yes
CursorBundled with your assistant0YesNoCompare →
Claude CodeBundled with your assistant0NoNoCompare →
EllipsisDedicated AI reviewer2NoSelf-hostable
QodoDedicated AI reviewer1—No
Gemini Code AssistBundled with your assistant0—No
SourceryDedicated AI reviewer0—No
BitoDedicated AI reviewer0NoNo

When each fits: AI coding agents

The whole decision →

Where the agent runs, and whose models it is tied to. A terminal agent works in your checkout on your machine, so you watch it, approve commands and stop it mid-task; a cloud agent takes the task to its own VM and returns a branch or pull request, so you can run several at once but review only the result. Most agents from a model lab use that lab's models and are paid through its subscription; the open-source, model-agnostic agents work with any provider or a local model, and the bill is whatever your API keys cost. AI-first editors and editor plugins are on their own page, AI Code Editors.

GitHub Copilot (Cloud agent): Assigning a GitHub issue to Copilot's cloud agent and getting a pull request back — also from Slack, Jira or Linear — or running the Copilot CLI in a terminal, on the Copilot plan you may already have for your editor. Trade-off: The cloud agent is built around GitHub repositories and issues, and agent sessions draw on your plan's AI credits.

Claude Code

Terminal agent
From $20/mollms.txt

Best forHanding off multi-step tasks — features, refactors, bug hunts — to an agent that reads the repo, edits files and runs commands, with web sessions for running tasks in the cloud.

Trade-offUses Anthropic models only, and needs a Claude subscription or API credits.

Used by 772 makers' products for this · GitHub Copilot vs Claude Code →

OpenAI Codex

Terminal agent
Open sourceFree tierFrom $8/mollms.txt

Best forDelegating tasks to an agent in the terminal, IDE or desktop app, or to cloud tasks that run in the background and open pull requests.

Trade-offBuilt around OpenAI models, and usage limits depend on your ChatGPT plan.

Used by 145 makers' products for this · GitHub Copilot vs OpenAI Codex →

OpenCode

Terminal agent
Open sourceFree tierFrom $10/moCLI

Best forAn open-source coding agent that works with almost any model provider, local models, or an existing Copilot or ChatGPT subscription.

Trade-offResult quality depends on the model you connect, and you manage provider keys and costs yourself.

Used by 44 makers' products for this

Pi

Terminal agent
Open sourceFree tier

Best forA deliberately minimal open-source (MIT) terminal agent that works with 15+ model providers through API keys or existing subscriptions, extended with packages instead of built-in features.

Trade-offNo sub-agents or plan mode out of the box; you add what you need, and results depend on the model you connect.

Used by 4 makers' products for this

Gemini CLI

Terminal agent
Open sourceFree tierllms.txtCLI

Best forAn open-source terminal agent on Gemini models with a free tier, for reading the repo, editing files and running commands.

Trade-offBuilt around Gemini models, and the free tier has daily request limits.

No maker product tracked for this yet

goose

Terminal agent
Open sourceFree tier

Best forAn open-source (Apache-2.0) agent as a desktop app, CLI and API, for coding and other workflows, with 15+ providers or an existing Claude, ChatGPT or Gemini subscription, and 70+ MCP extensions.

Trade-offA general-purpose agent rather than a coding specialist; it moved from Block to the Agentic AI Foundation, so older docs and links point to block.github.io.

No maker product tracked for this yet

Aider

Terminal agent
Open sourceFree tier

Best forThe original open-source terminal pair programmer, which edits files in your git repo with your own model keys or local models and commits every change.

Trade-offNo release since February 2026 and only occasional fixes since, so newer agent features are missing.

Used by 1 maker's product for this

Amp

Terminal agent

Best forA coding agent in the terminal and editors, with runs in the cloud for longer tasks.

Trade-offClosed source; spun out of Sourcegraph in December 2025, so older docs and packages still carry the Sourcegraph name.

No maker product tracked for this yet

Devin

Cloud agent

Best forHanding a whole task to an agent that works in its own cloud environment and comes back with a pull request.

Trade-offClosed source; you review its work after the fact rather than step by step. Its desktop editor is Devin Desktop (formerly Windsurf).

No maker product tracked for this yet

Jules

Cloud agent

Best forAsynchronous tasks on a GitHub repo, run in a Google cloud VM, with a REST API and CLI to start them.

Trade-offGoogle calls it experimental; limits depend on your Google AI Pro or Ultra plan.

No maker product tracked for this yet

Factory

Cloud agent

Best forCoding agents you can start from the terminal, the web, Slack or Linear, through to a pull request.

Trade-offPaid plans from $20 a month; the agent itself is closed source.

No maker product tracked for this yet

OpenHands

Cloud agent
Open sourceFree tierllms.txtCLI

Best forAn open-source (MIT) control center for running coding agents — its own, or Claude Code, Codex and Gemini CLI — on your laptop, in Docker, on a server or in OpenHands Cloud, including automations triggered by schedules or GitHub events.

Trade-offThe open-source version is single-user with no built-in auth for sharing; you run and secure the backend yourself, and results depend on the model you connect.

No maker product tracked for this yet

Kimi Code

Terminal agent
Open source

Best forMoonshot's coding agent — CLI, desktop app and VS Code extension — on its Kimi K3 model, included in Kimi membership.

Trade-offNo free plan; it shares your Kimi membership quota, and it replaced the older Python Kimi CLI, so older guides don't apply.

No maker product tracked for this yet

Mistral Vibe CLI

Terminal agent
Open source

Best forMistral's minimal open-source (Apache-2.0) terminal agent on its Devstral coding models.

Trade-offNeeds a Mistral API key or plan, and the Free plan allows only limited coding sessions; "Vibe" is also the new name of Mistral's chat app, which makes searching confusing.

No maker product tracked for this yet

Grok Build

Terminal agent
Open source

Best forxAI's open-source terminal agent on Grok models, which also runs headless and over ACP inside editors.

Trade-offBuilt around Grok models, and prices and limits are set by xAI's plans, which we couldn't read on its site.

No maker product tracked for this yet

Crush

Terminal agent
Free tier

Best forCharm's terminal agent with many model providers, language-server context and MCP support.

Trade-offSource-available under FSL rather than open source; terminal only.

No maker product tracked for this yet

Qwen Code

Terminal agent
Open source

Best forThe Qwen team's open-source (Apache-2.0) terminal agent, with VS Code, Zed and JetBrains integrations, built for Qwen models and usable with other providers.

Trade-offThe free Qwen OAuth tier ended in April 2026, so you now bring a provider key or a paid plan.

No maker product tracked for this yet

Oh My Pi

Terminal agent
Open sourceFree tier

Best forA fork of Pi with more built in — language-server and debugger tools, 60+ providers — for people who like Pi's approach but want fewer packages to assemble.

Trade-offA one-team fork that has to keep up with Pi; smaller community than the original.

No maker product tracked for this yet

Codegen

Cloud agent

Best forA platform for orchestrating coding agents in the cloud for teams — now part of ClickUp.

Trade-offCodegen has joined ClickUp, and codegen.com is now mostly a directory of other AI coding tools.

No maker product tracked for this yet

When each fits: AI code editors

The whole decision →

Switch to an AI-first editor, or add AI to the editor you already use. AI-first editors build the agent, completions and review into the editor itself, mostly as VS Code forks that import your extensions, and are where new agent features land first; editor plugins bring an agent into VS Code or JetBrains IDEs without changing editors, often with your own model keys and no seat fee. The terminal agents from AI Coding Agents also ship as editor extensions, which is a third way in if you already use one.

GitHub Copilot (Editor plugin): Adding AI completions, chat and agent mode to the editor you already use — VS Code, JetBrains IDEs, Xcode, Neovim — on a free tier to start. Trade-off: Deeper agent features vary by editor and land in VS Code first, and heavy use counts against plan limits.

Cursor

AI-first editor
Free tierFrom $8/mollms.txt

Best forA VS Code-style editor with AI completions, chat and agents built in, keeping your VS Code extensions, with cloud agents and Bugbot pull request review on the same plan.

Trade-offPlans are now sold together with xAI's Grok and X subscriptions — the $8 Plus plan runs Grok models only, and other providers' models are billed separately at API list price.

Used by 542 makers' products for this · GitHub Copilot vs Cursor →

Zed

AI-first editor
Open sourceFree tierFrom $10/mollms.txt

Best forA fast, open-source native editor with built-in AI edit predictions and agent chat, and a choice of models.

Trade-offSmaller extension ecosystem than VS Code.

Used by 32 makers' products for this

Google Antigravity

AI-first editor
Free tierllms.txt

Best forAn editor from Google with a manager view for running several coding agents in parallel, plus a CLI.

Trade-offTied to a Google account, and newer than the other editors, so features and usage limits are still changing.

Used by 13 makers' products for this

Kiro

AI-first editor
Free tierFrom $20/user/mollms.txt

Best forSpec-driven development, where the agent turns a prompt into requirements, a design and a task list before writing code, in a VS Code-compatible editor from AWS.

Trade-offThe spec process is slower than chatting for small changes, and paid use is billed in credits. AWS is retiring the Amazon Q Developer IDE plugins in favour of Kiro.

Used by 6 makers' products for this

Cline

Editor plugin
Open sourceFree tierFrom $9.99/mollms.txtCLI

Best forAn open-source agent inside VS Code, JetBrains IDEs or other VS Code-based editors that plans and makes multi-file changes, running commands with your approval, on the model provider of your choice.

Trade-offResult quality and cost depend on the model you connect, and long agent tasks on API keys can get expensive.

Used by 3 makers' products for this

JetBrains Junie

Editor plugin
Free tierFrom $8.33/mo

Best forJetBrains' own coding agent, inside IntelliJ IDEA, PyCharm and the other JetBrains IDEs and as a CLI, with a plan mode and GitHub and GitLab CI integrations.

Trade-offBeyond the free Junie Lite, you pay through JetBrains AI plans (from $8.33/user/month billed annually) or your own model keys.

No maker product tracked for this yet

Kilo Code

Editor plugin
Open sourceFree tierFrom $19/mollms.txtCLI

Best forAn open-source agent for VS Code, JetBrains IDEs and the terminal with access to 500+ models, through your own keys, local models or Kilo's gateway at provider rates.

Trade-offYou manage model choice and spend yourself, and the many modes and options take time to learn.

Used by 11 makers' products for this

Trae

AI-first editor
Free tierFrom $20/mo

Best forA VS Code-style editor with an agent window for parallel tasks and a SOLO mode where the agent plans and builds a feature end to end, on GPT, Gemini, Kimi, DeepSeek and other models.

Trade-offAvailable only in listed countries, paid usage is billed by tokens against a dollar allowance, and the product is mid-rename and merging with its TraeWork app.

Used by 8 makers' products for this

Augment Code

Editor plugin
From $20/mollms.txtCLI

Best forAn agent for VS Code, JetBrains IDEs and the terminal that indexes the whole codebase, for working in large or unfamiliar repositories.

Trade-offNo free plan, usage counts against the plan's included credits, and the homepage now leads with Cosmos, its cloud agent platform for teams.

Used by 7 makers' products for this

Continue

Editor plugin
Open sourceFree tier

Best forAn open-source (Apache-2.0) agent for VS Code and JetBrains IDEs plus the `cn` CLI, with your choice of models.

Trade-offAcquired by Cursor; the repository is still updated, but its future as a separate product is unclear.

Used by 5 makers' products for this

Zencoder

Editor plugin
From $40/mo

Best forCoding agents in VS Code and JetBrains IDEs plus the Zenflow desktop app, with unlimited use of your own model keys on the paid plan.

Trade-offNo free plan, only a 7-day trial; Pro is $45 per user a month.

Used by 1 maker's product for this

Claude Code

Editor plugin
From $20/mollms.txt

Best forThe Claude Code agent inside VS Code, Cursor or JetBrains IDEs, with its diffs shown in the editor.

Trade-offAnthropic models only; the JetBrains plugin needs the CLI installed separately.

No maker product tracked for this yet · GitHub Copilot vs Claude Code →

OpenAI Codex

Editor plugin
Open sourceFree tierFrom $8/mollms.txt

Best forThe Codex agent as an extension for VS Code-based editors and JetBrains IDEs, able to hand tasks to Codex cloud.

Trade-offOpenAI models only, and limits depend on your ChatGPT plan.

No maker product tracked for this yet · GitHub Copilot vs OpenAI Codex →

Qoder

AI-first editor
Free tierFrom $20/mo

Best forAn agentic coding platform with its own editor, a JetBrains plugin, a CLI and a mobile app, sharing one account and credit plan.

Trade-offClosed source, paid plans are billed in credits, and it falls back to basic models when credits run out.

No maker product tracked for this yet

Tabnine

Editor plugin
Self-hostable

Best forAn enterprise assistant — completions, chat, agent, CLI — that can be installed privately, with plugins for VS Code, JetBrains IDEs, Eclipse and Visual Studio.

Trade-offAcquired by Tricentis in July 2026; tabnine.com now redirects to Tricentis and public pricing is gone.

No maker product tracked for this yet

Roo Code

Editor plugin
Open source

Best forAn open-source VS Code agent (a Cline fork) with switchable modes such as code, architect and debug, using your own model keys.

Trade-offShut down on 2026-05-15 and the repository archived; the README pointed users to the ZooCode fork or Cline.

No maker product tracked for this yet

Blackbox AI

Editor plugin

Best forAn AI coding assistant with web chat, code completion and a VS Code extension.

Trade-offPivoted to an enterprise inference platform; the coding assistant is no longer on its site.

No maker product tracked for this yet

Supermaven

Editor plugin

Best forVery fast code completion in VS Code, JetBrains IDEs and Neovim.

Trade-offAcquired by Cursor and sunset on 2025-11-21; subscriptions were refunded and VS Code users were sent to Cursor.

No maker product tracked for this yet

Sourcegraph Cody

Editor plugin

Best forCode assistance in VS Code and JetBrains that drew context from Sourcegraph's search over very large codebases.

Trade-offThe free and Pro plans ended on 2025-07-23 and users were pointed to Amp; there is no self-serve plan.

No maker product tracked for this yet

Sweep AI

Editor plugin

Best forAI autocomplete and a coding agent built for JetBrains IDEs.

Trade-offsweep.dev no longer resolves and the plugin has not been updated since 2026-02-06; no shutdown was announced.

No maker product tracked for this yet

Amazon Q Developer

Editor plugin

Best forAWS-centred code help in VS Code and JetBrains IDEs, the terminal and the AWS console.

Trade-offAWS ends support for the IDE plugins on 2027-04-30 and recommends Kiro instead.

No maker product tracked for this yet

When each fits: AI code review

The whole decision →

Dedicated reviewer, review platform, or the one bundled with tools you already pay for. A dedicated reviewer works on any major Git host and goes deepest on review itself; a review platform also changes how you open and merge pull requests (stacked PRs, merge queue); a bundled reviewer costs nothing extra if you already have a coding-assistant plan, but it is only as deep as that plan. An open-source reviewer you run yourself costs only the model calls, but the setup and tuning are yours.

GitHub Copilot (Bundled with your assistant): Requesting AI review on GitHub pull requests, or in your editor, as part of a Copilot plan you already have. Trade-off: Needs a paid Copilot plan, reviews use up plan usage, and there are fewer review-specific settings than in a dedicated reviewer.

Graphite

Review platform

Best forAI review together with stacked pull requests, a review inbox and a merge queue, for teams that open many small PRs.

Trade-offGitHub only; unlimited AI reviews start on the per-user Team plan, and stacking is a new workflow to learn.

Used by 13 makers' products for this

CodeRabbit

Dedicated AI reviewer

Best forLine-by-line review of every pull request on GitHub, GitLab, Bitbucket or Azure DevOps, plus reviews of local changes from the CLI or editor before you push.

Trade-offPer-developer pricing on private repos, and reviews can be noisy until you tune them with rules.

Used by 9 makers' products for this

cubic

Dedicated AI reviewer

Best forGitHub pull request review with plain-English custom rules, plus scheduled scans of the whole codebase.

Trade-offGitHub only; paid per developer on private repos beyond a small free tier.

Used by 9 makers' products for this

Greptile

Dedicated AI reviewer
Self-hostable

Best forReviews that use an index of your whole codebase, so comments can point out how a change affects code outside the diff.

Trade-offPer-seat pricing with review credits beyond a one-developer free plan; self-hosting only on Enterprise.

Used by 1 maker's product for this

PR-Agent

Open-source, self-run
Open source

Best forAn open-source reviewer you run as a CI action, webhook app or CLI, with the model provider and key of your choice.

Trade-offYou set it up and pay the model API directly; community-maintained, with fewer features than Qodo's hosted product.

No maker product tracked for this yet

Cursor

Bundled with your assistant
Free tierFrom $8/mollms.txt

Best forBugbot reviews on pull requests in GitHub, GitLab, Bitbucket, Azure DevOps or Cursor's own Origin hosting, with custom rules, from the same vendor as the Cursor editor.

Trade-offIncluded only from Cursor's $30/month Premium plan (Cursor plans are now sold together with xAI's Grok subscriptions); not available on Free or the $8 Plus plan.

No maker product tracked for this yet · GitHub Copilot vs Cursor →

Claude Code

Bundled with your assistant
From $20/mollms.txt

Best forPull request review by Claude, through a GitHub Actions workflow you control or the managed Code Review service, following rules in your CLAUDE.md.

Trade-offThe Actions workflow costs API tokens or subscription usage plus Actions minutes and is yours to tune; the managed service is for Team and Enterprise plans and is billed per review by token usage.

No maker product tracked for this yet · GitHub Copilot vs Claude Code →

Ellipsis

Dedicated AI reviewer
Self-hostableFrom Tokens + 10%

Best forManaged Claude Code and Codex agents defined in YAML in your repo and triggered by pull requests, schedules, Slack, Linear or Sentry, which you can set up as a custom reviewer.

Trade-offNo longer a ready-made reviewer — you configure the review agent yourself — and billing is model tokens at cost plus 10% and sandbox compute, with no flat price.

Used by 2 makers' products for this

Qodo

Dedicated AI reviewer

Best forPull request review with context from the whole codebase, also in the IDE and the terminal.

Trade-offClosed source and paid past the free tier; PR-Agent is now a separate community project, not Qodo's free tier.

Used by 1 maker's product for this

Gemini Code Assist

Bundled with your assistant

Best forPR summaries and reviews from a GitHub app, from the same Google assistant you may use in your editor.

Trade-offThe enterprise version of GitHub review is still in preview.

No maker product tracked for this yet

Sourcery

Dedicated AI reviewer

Best forReviews on GitHub and GitLab PRs that flag likely bugs, summarize changes, suggest fixes and scan for security issues.

Trade-offBilled per seat; the code review engine is closed source.

No maker product tracked for this yet

Bito

Dedicated AI reviewer
From $12/seat/month

Best forCodebase-aware pull request reviews on GitHub, GitLab and Bitbucket (including self-hosted), with the same reviewer in VS Code and JetBrains IDEs.

Trade-offNo free plan, only a 14-day trial; each seat includes 5K reviewed lines a month and charges $5 per 1K after; the company now leads with its model router.

No maker product tracked for this yet

Questions

What is the best alternative to GitHub Copilot?

It depends on what you need it for; we don't rank them. Among products launched in 2026, the most picked for AI coding agents instead is Claude Code (84%), and the most projects leaving GitHub Copilot on GitHub moved to Claude Code (40 pull requests). You're comfortable in a terminal and want to hand off whole tasks: Claude Code and OpenAI Codex. You already pay for ChatGPT: OpenAI Codex. You want to switch between model providers freely or keep your tools open source: OpenCode, Pi and goose.

Is there a free alternative to GitHub Copilot?

Yes. For AI coding agents, OpenAI Codex, OpenCode, Pi, Gemini CLI, goose, Aider and 3 more have a free tier a small product can start on.

Is there an open-source alternative to GitHub Copilot?

Yes. For AI coding agents: OpenAI Codex, OpenCode, Pi, Gemini CLI, goose, Aider and 6 more.

What is the cheapest alternative to GitHub Copilot?

For a team of 5 with 10,000 users, the cheapest is OpenAI Codex at $40 a month on ChatGPT Go, against $50 for GitHub Copilot on Pro. From each vendor's pricing page.

Do developers move from GitHub Copilot to these?

On GitHub, 66 public pull requests since Oct 2024 moved projects off GitHub Copilot: Claude Code (40), OpenAI Codex (14), Cursor (7) and OpenCode (5); 57 moved to GitHub Copilot. Each is a real code change in a public repo, by developers in general.