CtrlK
GitHub Copilot is an artificial intelligence (AI) coding assistant developed by GitHub and OpenAI. It provides autocomplete-style code suggestions, chat-based assistance, and autonomous agent capabilities directly within a developer's integrated development environment (IDE). Since its launch in 2021, Copilot has grown into one of the most widely adopted AI-powered developer tools in the world, surpassing 20 million total users by mid-2025 and generating over $2 billion in annual recurring revenue for Microsoft.
The tool was the first major commercial product to emerge from Microsoft's $1 billion investment in OpenAI. It analyzes the context of code being written, including comments, function names, and surrounding code, and generates suggestions ranging from single-line completions to entire functions and classes. Originally powered by OpenAI Codex (a descendant of GPT-3), GitHub Copilot has evolved into a multi-model platform that supports models from OpenAI, Anthropic, Google, and xAI.
The foundations of GitHub Copilot trace back to the development of the GPT family of large language models at OpenAI:
On June 29, 2021, GitHub announced GitHub Copilot as a technical preview, available exclusively as a Visual Studio Code extension. The tool was positioned as an AI "pair programmer" that could assist developers with real-time code suggestions. At launch, roughly 30% of its suggestions were accepted by testers as correct and bug-free.
The technical preview was powered by OpenAI Codex, a model derived from GPT-3 but fine-tuned on billions of lines of public source code from GitHub repositories. Codex was trained on code in over a dozen programming languages, with particularly strong performance in Python, JavaScript, TypeScript, Ruby, and Go.
Additional IDE support followed quickly:
In March 2023, GitHub announced Copilot X, a vision for the next generation of the tool. Copilot X introduced several new capabilities powered by GPT-4:
In November 2023, Copilot Chat was updated to use GPT-4 as its default model, replacing earlier GPT-3.5-based versions.
At GitHub Universe 2023 (November), GitHub also announced Copilot Enterprise at $39 per user per month, which added features like knowledge bases trained on an organization's own codebase, Copilot Chat on GitHub.com, and integration with internal documentation.
On December 18, 2024, GitHub launched a free tier for Copilot, making the tool accessible to any developer with a GitHub account. The free plan included 2,000 code completions and 50 chat messages per month, with access to Claude 3.5 Sonnet and GPT-4o. No credit card was required.
This move was widely seen as a response to growing competition from free tools like Codeium and the rapid rise of Cursor.
Throughout 2024, GitHub also began rolling out multi-model support, letting developers choose between different large language models for Copilot Chat. This included models from OpenAI, Anthropic (Claude), and Google (Gemini).
On February 6, 2025, GitHub announced agent mode for Copilot in VS Code. Unlike traditional code completion, agent mode could autonomously plan and execute multi-step tasks: reading files, proposing edits across multiple files, running terminal commands, monitoring test output, and auto-correcting errors in a loop until the task was complete.
On May 17, 2025, GitHub announced the coding agent, a more autonomous mode where users could assign a GitHub issue to Copilot. The coding agent would spin up a secure cloud development environment (powered by GitHub Actions), write the code, and open a draft pull request with commits pushed in real time. The coding agent also performed self-review using Copilot code review before opening the pull request.
By July 2025, GitHub Copilot surpassed 20 million total users, a 5 million increase in just three months.
When GitHub Copilot launched in 2021, it was powered exclusively by OpenAI Codex, a model fine-tuned from GPT-3 on a large dataset of publicly available source code. Codex could interpret natural language prompts and translate them into code, and it supported over a dozen programming languages.
The system works by analyzing context from the file currently being edited, including the code above and below the cursor, file names, import statements, comments, and related open files. This context is sent to the model, which returns one or more suggested completions.
Over time, GitHub moved away from a single-model architecture to a multi-model platform. As of early 2026, developers can choose from a range of models depending on their plan:
| Model | Provider | Notes |
|---|---|---|
| GPT-4.1 | OpenAI | Default model for chat, agent mode, and completions |
| GPT-4o | OpenAI | Fast, multimodal model |
| GPT-5 (preview) | OpenAI | Advanced reasoning, available in preview |
| o3 (preview) | OpenAI | Reasoning-focused model |
| Claude 3.5 Sonnet | Anthropic | Strong coding performance |
| Claude 3.7 Sonnet | Anthropic | Extended thinking capabilities |
| Claude Opus 4 | Anthropic | Enterprise tier only |
| Gemini 2.5 Pro | Hosted on Google Cloud | |
| Gemini 3 Flash | Low-latency option | |
| Gemini 3 Pro | Full-featured Google model |
For inline code completions (the core autocomplete feature), GitHub uses a custom, smaller model optimized for low latency. The larger models listed above are primarily used for Copilot Chat, agent mode, and the coding agent.
GitHub Copilot supports code generation in virtually any programming language present in its training data, but performs best with:
| Language | Support Level |
|---|---|
| Python | Strong |
| JavaScript | Strong |
| TypeScript | Strong |
| Go | Strong |
| Ruby | Strong |
| Java | Strong |
| C / C++ | Strong |
| C# | Strong |
| Rust | Good |
| PHP | Good |
| Swift | Good |
| Kotlin | Good |
| Shell / Bash | Good |
| SQL | Good |
The original and most fundamental feature of GitHub Copilot is inline code completion. As a developer types, Copilot analyzes the context and offers suggestions that can range from completing a single line to generating entire functions, classes, or code blocks. Developers can accept suggestions with Tab, cycle through alternatives, or dismiss them.
Copilot adapts to the coding style and patterns in the current file and project. It can infer intent from comments written in natural language and generate corresponding code implementations.
Introduced in February 2025, Next Edit Suggestions (NES) represents an evolution beyond traditional completions. Rather than simply completing the current line, NES predicts what the developer will want to edit next based on their recent changes. For example, if a developer renames a variable, NES will suggest updating all other references to that variable throughout the file. NES uses a custom model trained specifically for this purpose, incorporating edit history rather than just the current state of the code.
NES is available in VS Code, Visual Studio, JetBrains IDEs, Xcode, and Eclipse.
Copilot Chat is a conversational interface embedded directly within supported IDEs and on GitHub.com. Developers can ask questions about their code, request explanations of complex logic, get help with debugging, and ask Copilot to generate or refactor code. Chat is context-aware, meaning it can reference the currently open file, selected code, terminal output, and error messages.
Chat supports multiple models and can be used in several modes:
Agent mode, announced in February 2025, transforms Copilot from a suggestion tool into an autonomous coding agent. When given a task in natural language, agent mode:
Agent mode supports Model Context Protocol (MCP) integration, allowing it to connect to external data sources and tools.
The coding agent, announced in May 2025 and made generally available in September 2025, goes further than agent mode by operating asynchronously in the cloud. Developers can assign a GitHub issue to Copilot (by tagging @copilot), and the coding agent will:
The coding agent can be extended with MCP servers to access external databases, APIs, and development tools.
Copilot code review allows developers to request an AI review of their pull requests directly on GitHub.com. Copilot analyzes the diff, identifies potential bugs, security issues, and style inconsistencies, and leaves review comments with suggested fixes. Organizations can configure automatic Copilot reviews for all pull requests, including those from contributors without a Copilot license.
As of 2025, Copilot code review is available in VS Code, Visual Studio, JetBrains IDEs, and via the GitHub CLI.
Copilot for CLI brings AI assistance to the command line. Developers can ask Copilot to explain commands, compose complex shell operations, and troubleshoot errors. The CLI supports natural language queries and returns executable commands with explanations.
Copilot CLI also supports MCP server integrations for custom tooling and plugins.
GitHub Copilot is available across a wide range of development environments. Feature availability varies by IDE:
| IDE | Code Completion | Chat | Agent Mode | Code Review | NES |
|---|---|---|---|---|---|
| Visual Studio Code | Yes | Yes | Yes | Yes | Yes |
| Visual Studio | Yes | Yes | Yes | Yes | Yes |
| JetBrains IDEs | Yes | Yes | Yes | Yes | Preview |
| Neovim / Vim | Yes | Yes | No | No | No |
| Xcode | Yes | Yes | No | No | Preview |
| Eclipse | Yes | Yes | No | No | Preview |
| Azure Data Studio | Yes | No | No | No | No |
| GitHub.com | N/A | Yes | N/A | Yes | N/A |
VS Code receives the most complete feature support, as both VS Code and Copilot are Microsoft products with tightly integrated development teams.
GitHub Copilot is available across five plan tiers as of early 2026:
| Plan | Price | Code Completions | Chat Messages | Premium Requests | Coding Agent | Code Review | Key Features |
|---|---|---|---|---|---|---|---|
| Free | $0 | 2,000/month | 50/month | None | No | No | Basic completions and chat; Claude 3.5 Sonnet and GPT-4o |
| Pro | $10/month | Unlimited | Unlimited | 300/month | Yes | Yes | Multiple model choices; unlimited suggestions |
| Pro+ | $39/month | Unlimited | Unlimited | 1,500/month | Yes | Yes | All Pro features plus expanded premium requests and GitHub Spark |
| Business | $19/user/month | Unlimited | Unlimited | 300/user/month | Yes | Yes | Organizational management; usage metrics; IP indemnity; data excluded from training |
| Enterprise | $39/user/month | Unlimited | Unlimited | 1,000/user/month | Yes | Yes | All Business features; knowledge bases; advanced models (Claude Opus); MCP server integration |
Premium requests are consumed when using advanced models (beyond the default) or when using features like the coding agent. Verified students, educators, and maintainers of popular open-source projects receive Copilot Pro for free.
In 2025, GitHub integrated support for the Model Context Protocol (MCP) across Copilot's agent features. MCP is an open standard that defines how applications share context with large language models, providing a standardized way to connect AI models to external data sources and tools.
With MCP, teams can extend Copilot's capabilities by connecting it to databases, internal APIs, documentation systems, and third-party services. MCP servers can be configured in VS Code, JetBrains IDEs, and the Copilot CLI.
GitHub also launched the GitHub MCP Registry, a curated directory of MCP servers from partners and the community. Developers can browse the registry to discover integrations that fit their workflow.
In September 2025, GitHub deprecated its earlier Copilot Extensions framework (based on GitHub Apps) in favor of MCP, signaling a broader industry shift toward standardized AI tool integration.
GitHub Copilot has seen rapid adoption since its launch:
| Metric | Value | Date |
|---|---|---|
| Total users | 20+ million | July 2025 |
| Paid subscribers | 4.7 million | January 2026 |
| Fortune 100 adoption | ~90% | 2025 |
| Annual recurring revenue | $2 billion+ | 2025 |
| Code written by Copilot (active users) | ~46% | 2025 |
| Year-over-year user growth | ~400% | Early 2024 to early 2025 |
| AI coding tool market share | ~42% | 2025 |
In 2024, Microsoft CEO Satya Nadella stated that GitHub Copilot had become a larger business than all of GitHub was at the time Microsoft acquired GitHub in 2018 for $7.5 billion. Copilot accounted for over 40% of GitHub's revenue growth during that period.
Multiple research studies have examined GitHub Copilot's effect on developer productivity, with results that are generally positive but nuanced.
A 2023 study published by researchers at Microsoft found that developers with access to GitHub Copilot completed a coding task 55.8% faster than a control group without Copilot. The study used a randomized controlled trial with professional developers.
A separate study across three companies found a 26.08% increase in the number of tasks completed by developers using Copilot, with the largest productivity gains observed among less experienced developers.
GitHub's own research found that between 60% and 75% of Copilot users reported feeling more fulfilled with their work, less frustrated when coding, and better able to focus on satisfying tasks. 73% of users said Copilot helped them stay in a state of flow, and 87% said it reduced mental effort during repetitive coding tasks.
Not all research has been uniformly positive. A study by Uplevel Data Labs found that while developers reported subjective productivity improvements, Copilot users had a significantly higher bug rate compared to non-users, and raw throughput (measured by pull requests) remained roughly constant. This suggested that Copilot might sometimes trade code quality for speed.
A Microsoft internal study similarly found limited measurable telemetry impact on throughput, though developers consistently reported perceived productivity gains, particularly for boilerplate and repetitive code.
Researchers have identified several security-related concerns with AI-generated code from Copilot.
An empirical study analyzing Copilot-generated code snippets on GitHub found that 29.5% of Python snippets and 24.2% of JavaScript snippets contained security weaknesses. These spanned 43 Common Weakness Enumeration (CWE) categories, including:
A 2025 study evaluating Copilot's own code review feature found that it frequently failed to detect critical vulnerabilities like SQL injection, cross-site scripting, and insecure deserialization. Instead, the automated reviews tended to focus on low-severity issues such as coding style and typographical errors.
A controlled user study found that developers using Copilot were more likely to submit insecure code compared to developers coding without AI assistance. Notably, these developers also expressed higher confidence in the security of their submissions, despite the presence of vulnerabilities.
Analysis of roughly 20,000 repositories with active Copilot usage found that over 1,200 (6.4%) had leaked at least one secret (such as API keys or credentials). This rate was 40% higher than the baseline across all public repositories, likely because Copilot can suggest code patterns that inadvertently expose sensitive data.
GitHub has responded to these concerns by adding secret scanning features and encouraging organizations to use Copilot's content exclusion settings to prevent sensitive files from being sent to the model.
In November 2022, the Joseph Saveri Law Firm and attorney Matthew Butterick filed a class-action lawsuit in the U.S. District Court for the Northern District of California against GitHub, Microsoft, and OpenAI. The lawsuit was filed on behalf of open-source programmers who alleged that Copilot's training data, sourced from public GitHub repositories, violated the licensing terms attached to that code.
The core legal argument was that Codex and Copilot were trained on billions of lines of open-source code without complying with the requirements of licenses like the GPL, MIT License, and Apache License. These licenses typically require attribution, inclusion of the license text, or other conditions that Copilot did not fulfill when reproducing or paraphrasing code.
In January 2024, the district court dismissed the majority of the original 22 claims, including most DMCA (Digital Millennium Copyright Act) allegations. Judge Tigar ruled that plaintiffs had failed to show that Copilot distributed code without copyright management information. However, the court allowed claims under DMCA Section 1202(a)(1) to proceed.
In July 2024, the court dismissed additional DMCA copyright claims, further narrowing the case.
In April 2025, plaintiffs filed an appeal to the U.S. Court of Appeals for the Ninth Circuit. The central question on appeal was whether Sections 1202(b)(1) and 1202(b)(3) of the DMCA impose an "identicality" requirement, meaning whether copies produced by an AI model must be identical to the original for liability to attach. The outcome of this appeal could set an important precedent for AI training and code generation across the industry.
In response to legal concerns, GitHub introduced IP indemnity for Copilot Business and Enterprise customers. Under this policy, Microsoft assumes legal liability if Copilot generates code that results in an intellectual property infringement claim, provided the customer is on a qualifying plan.
The AI coding assistant market has grown significantly since Copilot's launch, with several competitors offering alternative approaches:
| Tool | Developer | Pricing (Individual) | Key Differentiator |
|---|---|---|---|
| GitHub Copilot | GitHub / Microsoft | Free to $39/month | Largest user base; deep GitHub integration; multi-model support |
| Cursor | Anysphere | $20/month | Fork of VS Code with AI-native editor; strong agent capabilities |
| Claude Code | Anthropic | Usage-based | Command-line tool; autonomous multi-step coding; deep codebase understanding |
| Windsurf | Codeium | $15/month | AI-native IDE; "Cascade" agentic flow |
| Codeium | Exafunction | Free (unlimited) | Free tier with unlimited completions; strong privacy guarantees |
| Amazon Q Developer | Amazon | Free to $19/month | Deep AWS integration; code transformation for Java upgrades |
| Tabnine | Tabnine | Free to $12/month | On-premise deployment; privacy-first approach |
| Gemini Code Assist | Free to $19/user/month | Google Cloud integration; Gemini model access |
Cursor emerged as Copilot's most visible competitor in 2024 and 2025, gaining popularity for its AI-native editor approach and strong agentic coding features. Claude Code, released by Anthropic, took a different approach as a terminal-based tool focused on autonomous coding.
Despite increasing competition, GitHub Copilot maintained approximately 42% market share among paid AI coding tools as of 2025, benefiting from its first-mover advantage and integration with the GitHub ecosystem used by over 100 million developers.
In April 2024, GitHub launched a technical preview of Copilot Workspace, an experimental browser-based development environment. Given a GitHub issue written in natural language, Copilot Workspace could generate a specification, propose a plan, and produce actual code changes, all within a browser interface.
Copilot Workspace used multiple specialized AI agents for different stages of the workflow:
The technical preview was sunset on May 30, 2025. GitHub took the architectural lessons learned (sub-agent design, issue-to-pull-request workflow, asynchronous execution) and rebuilt them into the Copilot coding agent, which became generally available in September 2025.
GitHub Copilot is used across a wide range of software development scenarios: