Updated

GitHub Copilot

An AI coding assistant integrated into editors and GitHub, providing code completion, chat, and agent-based workflows.

27 makers' products we track use GitHub Copilot. For AI coding agents it's 4th most chosen of 6 options: 27 of the 909 makers' products we know the AI coding agents of (3%). Among the 657 launched in 2026, 2% chose it, against 6% of those launched in 2024 or earlier. 173 open-source projects also declare it in their code. What makers like most: Inline completions work in every major IDE, including Vim and Visual Studio, cutting boilerplate as you type. Their most common complaint: The switch to usage-based billing made it far worse value, driving people to other tools. On GitHub, 57 public pull requests moved projects to GitHub Copilot from tools we list, and 66 moved them away.

Free tierPaid from $10/mo

Profile checked

Works with AI agents:llms.txt
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use GitHub Copilot

Makers' products we track use GitHub Copilot for AI coding agents (27), most often alongside Amazon Web Services (19%).

What GitHub Copilot is used for

AI Code Editors · 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.
AI Code Review · 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.
Graphite13CodeRabbit9cubic9Ellipsis2Greptile1GitHub Copilot0Makers' products on each, for AI code review
AI Coding Agents · 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 Code772OpenAI Codex145OpenCode44GitHub Copilot27Pi4Makers' products on each, for AI coding agents

GitHub Copilot vs the alternatives makers chose

For AI coding agents, 27 of the 909 makers' products we know the choice of picked GitHub Copilot (3%), behind Claude Code (85%). Among those launched in 2026 it's 2%.

OptionMakers' products2026 launchesFree forTeam of 5, 10,000 usersOpen source
Claude Code772 85%84%None$100/mo · ProNoCompare →
OpenAI Codex145 16%19%None$40/mo · ChatGPT GoYesCompare →
OpenCode44 5%5%None$50/mo · GoYes
GitHub Copilot27 3%2%None$50/mo · ProNo
Pi4 0%0%——Yes
Aider1 0%0%——Yes

For AI coding agents: how many of the 909 makers' products we know the AI coding agents of chose each option, and the share among the 657 launched in 2026, since a tool that came first has products from every year, and what each costs for a team of 5 with 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

Often paired with

Share of the 27 makers' products on GitHub Copilot that show this choice.

Markets that build with it most

Product Hunt markets where GitHub Copilot is in far more of the stacks we know than across every market (1%).

When to use GitHub Copilot, and when not

Pick GitHub Copilot if

Something else fits better if

  • You're comfortable in a terminal and want to hand off whole tasks: Claude Code or OpenAI Codex.
  • You already pay for ChatGPT: OpenAI Codex.
  • You want to switch between model providers freely or keep your tools open source: OpenCode or Pi or goose.
  • You want to try a terminal agent without paying for a subscription: Gemini CLI.
  • Tasks arrive in Slack, Linear or a ticket tracker and you want an agent to pick them up there: Devin or Factory.
From each decision's guide, written from what makers' products chose and why.

GitHub Copilot is GitHub's AI assistant for writing and shipping code. It suggests code as you type, answers questions in chat, edits your local project in agent mode, and has a cloud agent you can assign an issue to so that it returns a pull request. Because it is built into GitHub, a change can go from issue to agent to pull request to Copilot code review without leaving the platform.

More about GitHub Copilot

It runs as an extension in VS Code, Visual Studio, JetBrains IDEs, Vim/Neovim, Xcode and Azure Data Studio, and also in Copilot CLI, on GitHub.com and in GitHub Mobile. Agent mode works in your local environment, while the cloud agent works in an ephemeral environment powered by GitHub Actions, where it can run tests and linters before opening a pull request. You steer it with repository instructions, custom agents, skills and MCP servers, and third-party agents such as Codex and Claude can work under the same protections.

For a small team, Copilot Business adds admin policies for features and models, plus content exclusion to keep chosen files out of suggestions and reviews. Bring-your-own-key lets VS Code, JetBrains, Xcode and the CLI use models from other providers or on your own machine. It is a service hosted by GitHub.

The cloud agent only works on repositories hosted on GitHub, changes one repository and one branch per task, and can be blocked by incompatible rulesets. Interactions on Free, Pro and Pro+ may be used for training unless you opt out.

GitHub Copilot pros and cons

What makers like most: Inline completions work in every major IDE, including Vim and Visual Studio, cutting boilerplate as you type. Their most common complaint: The switch to usage-based billing made it far worse value, driving people to other tools.

Pros

  • Inline completions work in every major IDE, including Vim and Visual Studio, cutting boilerplate as you type. PHPH 2
  • One subscription gives a choice of models from several labs, including some free ones. PHHN
  • Deep editor integration, such as a semantic index of the solution in Visual Studio and a read-only plan mode in VS Code. HNHN 2PH
  • Companies can approve it for compliance, and it offers copyright indemnity. HNHN 2
Product Hunt review tags
productivity boost5
suggests code snippets4
focus on problem-solving3
reduces boilerplate3
accelerates development process2
integrates with major IDEs2

Cons and watch-outs

  • The switch to usage-based billing made it far worse value, driving people to other tools. HNHN 2HN 3HN 4
  • As an agent harness it trails Claude Code and Codex, with truncated or bloated context that confuses models. HNHN 2HN 3HN 4
  • Built-in pull request review misses too much and raises many wrong findings. HN
  • Completion quality has slipped, for example repeatedly reverting newer language syntax. HNHN 2

Themes that recur in makers' words and Hacker News comments, each linked to what it summarises, with how Product Hunt tags its reviews.

4.8★ from 35 reviews on Product Hunt ↗

What Hacker News says about GitHub Copilot

On Hacker News, 23% of comments about GitHub Copilot recommend it and 23% criticize it: net praise −0%, 7th best liked of 9 tools HN discusses for AI coding agents.

By year

YearComments choosing it, per monthNet praise
202315+27%
202415−8%
2025260%
2026 (8 mo)22−18%

In their words

  • “GitHub Copilot has a "steer with message" feature where I can course correct mid execution. I use it often.” HN, May 2026
  • “Quite honestly I love the GitHub Copilot CLI. I pair it with Squad and it’s awesome.” HN, Apr 2026
  • “GitHub Copilot costs have ballooned in recent week, what once took $100 requires $300.” HN, Jul 2026

Hacker News comments January 2023 to August 2026 that name GitHub Copilot in a sentence like "I use" or "we moved to", Claude read a sample of 100 and the counts scale it to all of them; net praise is comments recommending it minus comments criticizing it, as a share of all comments about it. How it's counted, and how HN compares with makers.

Who switches

More projects move away from GitHub Copilot: 57 pull requests in, 66 out; the most come from Claude Code and leave for Claude Code.

Moving to GitHub CopilotMoving away
GitHub Copilot
Claude Code → GitHub Copilot28 PRs
OpenAI Codex → GitHub Copilot22 PRs
OpenCode → GitHub Copilot7 PRs
GitHub Copilot → Claude Code40 PRs
GitHub Copilot → OpenAI Codex14 PRs
GitHub Copilot → Cursor7 PRs
GitHub Copilot → OpenCode5 PRs

Public pull requests on GitHub since Oct 2024 whose title says "X to Y" — real code changes moving a project from one tool to another, by developers in general.

Apps built with GitHub Copilot

27 makers' products, each linked to the source that shows it, and 173 open-source projects that declare it in their code. The best known on Product Hunt: Crono (1,723 followers), Beatoven.ai (1,662 followers), Edgee (1,315 followers), Stash (797 followers), Kastra (721 followers).

The maker says so 26Job posting 1Declared in code 173How evidence is collected →
Edgee
EdgeeOne gateway for cheaper, faster, unstoppable coding agents

“Our token compression technology has to be compatible and efficient with Github Copilot, so we have to use it extensively to understand how we can optimize its context.”

AI Coding AgentsMaker says so · source ↗
Perfai Security
Perfai SecurityFind & fix live vulnerabilities in Vibe Apps with 1-prompt.

“We compliment Github Copilot with our security solution built for vibe-coders using the platform.”

AI Coding AgentsMaker says so · source ↗
Bolt
BoltThe home of Bolt Checkout and the Bolt SuperApp

“AI-powered suggestions that speed up coding and reduce boilerplate, available in all major IDEs.”

AI Coding AgentsMaker says so · source ↗
Beatoven.ai
Beatoven.aiGenerates background music from text prompts, for creators who need music for videos and…

“I’m absolutely loving GitHub Copilot because it suggests code snippets right as I type, saving me a ton of time and letting me focus on bigger problems. It feels like I’m pair-programming with an AI that’s got my back at all times. It integrates seamlessly with my favorite IDE, and compared to other tools I’ve tried, the suggestions feel a lot more relevant and accurate.”

AI Coding AgentsMaker says so · source ↗
Kastra
KastraRuntime authorization for Claude, Cursor, Codex and OpenClaw

“Supported us in understanding the complex infra problems we needed to solve to make Kastra operate at low latency.”

AI Coding AgentsMaker says so · source ↗
PeakRoutine
PeakRoutinePersonalized health coaching powered by your biomarkers

“Amazing tool to which gives you the flexibility to choose between different models”

AI Coding AgentsMaker says so · source ↗
FeedPal
FeedPalAuto-subscribe to bookmarked blogs

“GitHub Copilot is an ingenious coding companion that effortlessly boosts productivity with its uncanny ability to suggest spot-on code completions.”

AI Coding AgentsMaker says so · source ↗
Gleo AI
Gleo AIGuide to improve communication skills with roleplay

“Much appreciated, to reduce hours of work in minutes at certain instances.”

AI Coding AgentsMaker says so · source ↗
Gym Hero
Gym HeroThe Future of Gym Tracking—Private, Smart, On-Device AI.

“I use GitHub Copilot to speed up development, generate boilerplate Swift code, and optimize algorithms. It helps me focus on Gym Hero’s core features by suggesting code completions and automating repetitive tasks.”

AI Coding AgentsMaker says so · source ↗
scritty
scrittyShared, searchable memory for every AI coding agent

“Copilot was the first agent I ran inside scritty every day; it set the bar for what a CLI agent's capture and replay had to feel like.”

AI Coding AgentsMaker says so · source ↗
Stash
StashGives you context from your codebase, issues, and docs

“Copilot is everywhere, but it often works in isolation. Stash MCP bridges it to your team’s repos, issues, and docs. Making Copilot way more context-aware.”

AI Coding AgentsMaker says so · source ↗
Cloudback
CloudbackAutomatic backups and restores for Git and Linear

“Cloudback's MCP server plugs into GitHub Copilot's agent mode in VS Code, so you can manage your backup definitions, schedules, and retention straight from Copilot chat without leaving the editor.”

AI Coding AgentsMaker says so · source ↗
CherryPick
CherryPickEasily organize your contacts; CherryPick your success

“Shoutout to GitHub Copilot that helped me bring the project back to life.”

AI Coding AgentsMaker says so · source ↗
Crono
CronoThe Agentic Sales Engine

“GitHub Copilot is like having an AI-powered pair programmer always by your side. It speeds up coding, suggests smart solutions, and makes development smoother than ever. A game-changer for engineers!”

AI Coding AgentsMaker says so · source ↗
dibma / Joki Strava
dibma / Joki StravaFake your runs and flex on Strava

“GitHub Copilot has been an incredible pair programmer throughout the building of this app. It helped me scaffold features faster, suggest cleaner implementations, and stay in the flow instead of getting stuck on boilerplate or minor bugs.”

AI Coding AgentsMaker says so · source ↗
Pinetree(Beta)
Pinetree(Beta)Pinetree is browser-based hierarchical markdown editor

“This launch wouldn’t have been possible without GitHub Copilot. It completely changed the way I think about programming — and I've been developing software for over 20 years. Pairing with AI has become one of the most exciting experiences in my career. Copilot dramatically accelerated our development process and helped us reach launch speed we never thought possible. It may be the tool that replaces my job one day, but right now, it’s the best partner I could ask for.”

AI Coding AgentsMaker says so · source ↗
gg-friggin-ez
gg-friggin-ezFast & free profanity and toxicity screening via Jev & Laya

“My daily AI agentic workflow system that accelerated everything from core TypeScript architecture to the interactive browser HUDs and CI/CD pipelines.”

AI Coding AgentsMaker says so · source ↗
MockPilot
MockPilotTurn live websites into editable mockups

“GitHub Copilot offers users a variety of free LLM models through their GitHub accounts. This lets MockPilot users easily gain access to free LLMs just by logging into their GitHub account.”

AI Coding AgentsMaker says so · source ↗
Visual Studio 2026 Insiders
Visual Studio 2026 InsidersThe world’s most popular IDE just got smarter, faster

“In Visual Studio, Copilot isn’t just aware of your code; it understands your work. With full context across your solution, repo, and tools, it helps you move faster, think bigger, and build with confidence.”

AI Coding AgentsMaker says so · source ↗
packmind
packmindGone · site taken down on its host, Oct 2026Packmind seamlessly captures your engineering playbook and turns it into AI context, gua…AI Coding AgentsIn its code · source ↗

Open source: a project that declares GitHub Copilot as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

What open-source projects' AGENTS.md and CLAUDE.md files say about GitHub Copilot, in our words — from the 16 files that name it:

116 of the 116 open-source products built with GitHub Copilot that were worked on in the last 180 days keep instruction files for coding agents — 100%, against 53% of all the projects we read. AGENTS.md is in 92, CLAUDE.md in 63.

1,059words in the median file
pnpmthe package manager most named, in 21 of 95 files
73%say how to test a change
Named more in these files than in other projects' — in how many of the 95:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to GitHub Copilot

All alternatives by situation →

Further reading

Questions makers ask about GitHub Copilot

Is GitHub Copilot good for production?

27 makers' products we track run on it. On GitHub, 57 public pull requests moved projects to GitHub Copilot from tools we list, and 66 moved them away. The watch-out makers raise most: The switch to usage-based billing made it far worse value, driving people to other tools.

What is GitHub Copilot used for?

An AI coding assistant integrated into editors and GitHub, providing code completion, chat, and agent-based workflows. Makers' products we track use it for AI coding agents (27).

What are the pros and cons of GitHub Copilot?

Pros makers name: Inline completions work in every major IDE, including Vim and Visual Studio, cutting boilerplate as you type. One subscription gives a choice of models from several labs, including some free ones. Deep editor integration, such as a semantic index of the solution in Visual Studio and a read-only plan mode in VS Code. Cons: The switch to usage-based billing made it far worse value, driving people to other tools. As an agent harness it trails Claude Code and Codex, with truncated or bloated context that confuses models. Built-in pull request review misses too much and raises many wrong findings.

What are the alternatives to GitHub Copilot?

For AI coding agents, the other options makers' products we track chose most are Claude Code (772), OpenAI Codex (145), OpenCode (44), Pi (4), Aider (1). Open source or self-hostable among them: OpenAI Codex, OpenCode, Pi, Aider. Each alternative, with the situation it fits, is on the GitHub Copilot alternatives page.

Is GitHub Copilot still popular with new products?

Less than before: among the 657 makers' products launched in 2026 that made the AI coding agents choice, 2% chose GitHub Copilot, against 6% of the 62 launched in 2024 or earlier.

How much does GitHub Copilot cost per month?

For a team of 5 with 10,000 users, GitHub Copilot costs $50 a month on the cheapest plan that fits (Pro), from its pricing page.

Do developers switch to or away from GitHub Copilot?

On GitHub, 57 public pull requests moved projects to GitHub Copilot from tools we list, most from Claude Code (28), OpenAI Codex (22), OpenCode (7); 66 moved them away, most to Claude Code (40), OpenAI Codex (14), Cursor (7).

When should you use GitHub Copilot?

Tasks start as GitHub issues and you want pull requests back without running anything locally (AI coding agents). You don't want to change editors (AI code editors). You already pay for Copilot, Cursor or Claude and want review from the same tool (AI code review). Something else fits better if: you're comfortable in a terminal and want to hand off whole tasks, pick Claude Code or OpenAI Codex; you already pay for ChatGPT, pick OpenAI Codex.

Which editors does Copilot work in?

There are extensions for VS Code, Visual Studio, JetBrains IDEs, Vim/Neovim, Xcode and Azure Data Studio, plus Copilot CLI in the terminal. Chat and agent features vary by editor. source ↗

Is my code used to train models?

GitHub may use interactions on Copilot Free, Pro and Pro+, including inputs, outputs and code snippets, to train its models unless you opt out in your account settings. source ↗

Can the cloud agent work on GitLab or Bitbucket repositories?

No. The cloud agent only works with repositories hosted on GitHub, and each task is limited to one repository and one branch, ending in a single pull request. source ↗

What does the cloud agent use to run?

It runs in an ephemeral development environment powered by GitHub Actions, and uses Actions minutes plus AI credits that depend on the model and tokens used. source ↗

Can I keep certain files away from Copilot?

Yes, on Copilot Business and Enterprise. Content exclusion stops excluded files from getting suggestions, informing responses, or being reviewed, though it doesn't apply to symlinks or remote filesystems. source ↗

Can I use my own model provider or a local model?

Yes. Local bring-your-own-key in VS Code, JetBrains, Xcode, Copilot CLI and the Copilot app stores keys on your machine and can work without GitHub's Copilot API, and organization owners can add custom models for all users. source ↗

Is GitHub Copilot free?

Yes — there is a free tier a small product can run on; paid use starts at $10/mo. source ↗

Is GitHub Copilot open source or self-hostable?

Not open source, and hosted only.

Can AI coding agents work with GitHub Copilot?

It serves an llms.txt docs index.

Who uses GitHub Copilot?

27 makers' products we track, each with a source, and 173 open-source projects declare it in their code. The best known of them on Product Hunt: Crono (1,723 followers), Beatoven.ai (1,662 followers), Edgee (1,315 followers), Stash (797 followers), Kastra (721 followers). source ↗