GitHub Copilot is an AI coding assistant developed by GitHub, a subsidiary of Microsoft, that provides contextualized assistance across the entire software development lifecycle — from inline code suggestions in the editor to autonomous agent tasks and governance tooling for large engineering organizations. GitHub markets it as "your AI accelerator for every workflow, from the editor to the enterprise," and deliberately frames it as a "Copilot," not an "Autopilot": a tool built to augment developers' judgment rather than replace it.
Who builds it
Copilot is built by GitHub and is powered by generative AI models developed by GitHub, OpenAI, and Microsoft. GitHub itself operates as a subsidiary of Microsoft.
Core features
Copilot's feature set spans the coding workflow:
- Inline code suggestions and completions in the editor, with a code-referencing check that flags suggestions matching publicly available code.
- Copilot Chat, available inside IDEs, on GitHub.com, in GitHub Mobile, and in Windows Terminal, for explaining code, generating tests, and suggesting fixes.
- Agentic capabilities, including a cloud agent that can research a repository, draft an implementation plan, and make code changes, plus a "Fleet mode" for running multiple tasks in parallel.
- Copilot CLI for command-line development assistance.
- Automated code review on pull requests.
- Customization, via personal, repository, and organization-level custom instructions, custom agents with specialized expertise, and Model Context Protocol (MCP) integration for connecting external tools.
- Copilot Spaces for organizing project-specific context.
It integrates as an extension into Visual Studio Code, Visual Studio, JetBrains IDEs, Eclipse, Vim, Neovim, and Azure Data Studio, and is trained on the languages represented in public repositories, with GitHub noting that suggestion quality varies by how well a language is represented in that training data.
Pricing
GitHub Copilot follows a tiered subscription model with a genuine free tier:
- Free ($0): 2,000 completions per month, access to multiple AI models, Copilot CLI, and community support.
- Pro ($10/user/month): everything in Free, plus unlimited code completions, cloud agent access, code review, third-party agent integrations, and $15 of monthly AI credits.
- Pro+ ($39/user/month): everything in Pro, plus access to premium models (including Opus), audit logs, and $70 of monthly credits.
- Max ($100/user/month): everything in Pro+, plus priority access to new models and features, and $200 of monthly credits.
- Business and Enterprise: organization-level plans priced by contacting sales. Business covers IDE, CLI, and mobile usage; Enterprise adds GitHub.com integration, codebase indexing, and custom model fine-tuning.
Usage-based features such as chat, agents, and CLI draw on GitHub AI Credits, billed at $0.01 per credit, with the included monthly allowance scaling by plan.
Who it's for
GitHub positions Copilot as "the world's most widely adopted AI developer tool." On the individual side it targets developers, freelancers, students, educators, and open source maintainers. On the organizational side, Business and Enterprise plans add usage-based billing with budget controls, audit logging and compliance monitoring, MCP server governance, and policy controls — aimed at engineering teams that need to roll Copilot out with oversight. GitHub cites internal data claiming developers using Copilot report "up to 75% higher satisfaction with their jobs" and are "up to 55% more productive at writing code without sacrifice to quality," though these are vendor-reported figures rather than independently audited benchmarks.