GitHub Copilot
GitHub Copilot is GitHub's AI coding assistant. Official docs no longer describe it as "OpenAI Codex in VS Code". Today it is a suite: inline completions in the IDE, Copilot Chat, CLI and Windows Terminal chat, GitHub Mobile, a desktop Copilot app, and a cloud agent that can research a repo, open a branch, and draft a pull request. It also checks suggestions against public code and can attach a code reference or drop the match. This page replaces the 2021 Codex-only writeup.
Key Features
- IDE completions and chat: Type-ahead suggestions plus a chat that can use Copilot Spaces for shared context.
- Cloud agent: Research, plan, edit on a branch, then let you review the diff and open a PR.
- Surfaces: IDE, github.com, GitHub Mobile,
ghCLI, Windows Terminal Canary, and the Copilot desktop app. - Enterprise controls: Policy, centralized agent management, custom agents, automations, and geographic data residency on GitHub Enterprise Cloud.
- Not on Enterprise Server: Official plans page says Copilot is not currently available for GitHub Enterprise Server.
Use Cases
- Everyday GitHub shops that want completions where the code already lives.
- Async PR drafting via the cloud agent when you do not want to babysit a local CLI.
- Orgs that need residency and policy on Enterprise Cloud.
Pricing
GitHub Changelog 2026-08-28 says Copilot Business and Enterprise prices are not changing, and credit-card/PayPal org sign-ups reopen 2026-09-01. Usage-based GitHub AI Credits have been live for all plans since 2026-06-01.
| Plan | Price | Notes |
|---|---|---|
| Free | $0 | Limited completions and models via auto selection. Marketing also cites 2,000 completions/month. |
| Student | Free | Unlimited completions plus AI credit allowance; limited chat/agent models. |
| Pro | $10 / month | Unlimited completions, cloud agent, monthly AI credits. Some teachers and popular OSS maintainers may qualify free. |
| Pro+ | $39 / month | Higher credits and premium models. |
| Max | $100 / month | Highest individual credit allowance and priority access. |
| Business | $19 / granted seat / month | 1,900 AI credits per user on the org billing docs. Credit-card org sign-ups reopen 2026-09-01. |
| Enterprise | $39 / granted seat / month | Business plus larger credit pool and enterprise extras. |
Credits are usage-based beyond the included allotment. Confirm Plans for GitHub Copilot.
Getting Started
- Open github.com/settings/copilot and start Free, or request access from an org.
- Install the IDE extension or
gh copilot. Students should apply for the Student plan before paying Pro. - For unattended work, enable the cloud agent on a disposable branch and review the PR in GitHub.
- Enterprises: confirm you are on Enterprise Cloud. Server is not supported.
Frequently Asked Questions
Is Copilot still just Codex autocomplete?
No. Completions remain, but chat, CLI, mobile, a desktop app, and a cloud agent are first-party.
Can I use it without GitHub.com?
The product is tied to a GitHub account and, for orgs, to Cloud. It is not on Enterprise Server.
How does it compare to Claude Code?
Claude Code operates your local checkout across CLI and desktop. Copilot is GitHub-native and strongest when issues, PRs, and policy already live on github.com.
Alternatives
- Claude Code: Anthropic's repo agent.
- Codex CLI: OpenAI's terminal agent on ChatGPT plans.
- Cursor: Editor-native agent if you are not standardized on GitHub.
Tips
- Start on Free to measure completion quality before Pro.
- Treat cloud-agent PRs as drafts. Official flow is review, iterate, then merge.
- Confirm Business self-serve status. The 2026-04-22 pause may still apply.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights
Cursor vs GitHub Copilot: Complete Comparison 2026
In-depth comparison of Cursor and GitHub Copilot. Discover which AI coding assistant is best for your workflow with detailed feature analysis, pricing, and real-world testing.
Skills + Hooks + Plugins: How Anthropic Redefined AI Coding Tool Extensibility
An in-depth analysis of Claude Code's trinity architecture of Skills, Hooks, and Plugins. Explore why this design is more advanced than GitHub Copilot and Cursor, and how it redefines AI coding tool extensibility through open standards.
Seven AI Coding CLIs, Six Months: No Matter How Strong the Model, Work Needs Supervision
Claude Code, Codex, opencode, pi, omp and DeepSeek Harness all have personalities. After six months of deep use I run a division of labor: pi for the fastest cheapest reviews, omp for complex PRs, DeepSeek Harness on V4 Flash for high-frequency low-cost review, and Claude Code, Qoder and Cursor for writing. No matter how strong the model, work needs supervision — ideally from an independent third party.