Back to vendors
G

GitHub Copilot

Also known as: Copilot, Copilot coding agent, Copilot Workspace

Visit site
Entry pricePro from $10 a month, with a free tier. Business is $19 and Enterprise $39 per seat a month.Full pricing detail

GitHub's AI coding platform with cloud agents for autonomous PR lifecycle management, MCP support, model choice, and agentic coding from IDE through CI/CD.

GitHub Copilot is the AI coding assistant built by GitHub, the Microsoft-owned platform where much of the world's software is hosted. It began as an autocomplete-style pair programmer and has grown into a broad suite that spans the whole development lifecycle, from inline suggestions in the editor to autonomous agents that complete tasks on their own. It works across IDEs including VS Code, Visual Studio, JetBrains, Eclipse, and Xcode, as well as GitHub.com, a command-line interface, mobile, and chat tools like Slack and Teams.

At the everyday level, Copilot offers code completions and next-edit suggestions that predict and propose a developer's next change, plus a chat interface for explaining code, writing tests, and debugging. Copilot Edits applies natural-language changes across multiple files at once. In agent mode, Copilot picks the files to touch, proposes and runs terminal commands, reads the output, and iterates until a multistep task is done, attempting to fix its own build failures along the way.

Beyond the editor, Copilot can run work asynchronously. Its cloud agent takes an assigned issue, from GitHub Issues or tools like Jira, Linear and Azure Boards, or starts from an automation on a schedule or an event, researches the repository, makes changes on a branch in its own environment, runs tests, can open the app it is building in a browser through a built-in Playwright MCP server, and hands the diff back for review. Copilot Memory lets the cloud agent, code review and the CLI keep validated repository facts and user preferences that expire after 28 days unused, and an agentic code-review feature reads related files and dependencies before commenting on a pull request.

Developers can choose among models from OpenAI, Anthropic, Google, xAI, Moonshot AI and Microsoft, and third-party coding agents like Claude and Codex can run alongside Copilot's own. It supports the Model Context Protocol for connecting external tools and data, having replaced its older extension system, and a Copilot SDK exposes the agent loop to developers.

For organizations, Copilot adds policy and access controls, an agentic audit log, codebase indexing, data residency in the United States or the European Union, security scanning of generated code, and IP indemnity, with each plan including GitHub AI Credits and extra credits billed per use.

Vendor details

Canonical URL

https://github.com/features/copilot

Category

Coding agent

Company status

first party product

Use cases & customers

Target customers

developersenterpriseengineering leaders

Deployment options

SaaS (github.com)GitHub Enterprise Cloud with data residency (regional model endpoints)GitHub Enterprise Server (self-hosted)IDEs (VS Code, Visual Studio, JetBrains, Eclipse, Xcode)CLIMobileSlack and Teams

Integrations

MCP is Copilot's extensibility surface, having replaced the older extension system, with an enterprise MCP registry and policy controls over which servers may be connected. Copilot operates natively across GitHub Issues, pull requests, Actions and security alerts, takes task intake from Jira, Linear and Azure Boards, and reaches Slack and Teams. It runs in VS Code, Visual Studio, JetBrains, Eclipse and Xcode, on GitHub.com, in a CLI and on mobile, and runs third party coding agents including Codex and Claude alongside its own under the same protections.

In practice

You file an issue for a bug fix and don't want to stop your current work. Copilot's cloud agent picks it up, makes the changes on a branch, runs tests and scans for security issues, then hands the diff back so you decide when to open the pull request.

A task touches a dozen files and needs commands run to verify it. Copilot's agent mode chooses the files, makes cross-file edits, runs the terminal commands, reads the output, and iterates until the build passes.

Your team wants to use Claude or Codex alongside Copilot without juggling separate tools. On Copilot Pro and higher plans you assign tasks to Copilot, Claude or Codex and track the work of every agent from one workspace.

Agentic Index coverage score

13.5 / 14 capabilities · 96%

Integrations & Tool Calling Full

The cloud agent works natively across GitHub issues, pull requests and Actions, takes tasks from Slack, Teams, Jira, Linear and Azure Boards, and reaches further tools and data through MCP servers, with the GitHub and Playwright MCP servers on by default and enterprise policy restricting MCP servers.

Sourcedocs.github.com about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

Workflow Orchestration Full

The cloud agent researches, plans and changes code on a branch in its own environment, custom agents configured with tailored prompts, tools and context handle specialized tasks at enterprise, organization and repository level, and third party coding agents (Claude, Codex) run alongside it under the same protections.

Sourcedocs.github.com about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

Knowledge Grounding & RAG Full

Each repository gets a semantic code search index that is kept current automatically, typically updated within seconds of a new conversation, and used by Copilot Chat on GitHub and in VS Code and by the cloud agent; MCP extends grounding to outside data and content exclusions bound what may be read.

Sourcedocs.github.com concepts/context/repository-indexingread 2026-09-29

Human Oversight & Guardrails Full

The cloud agent works on a branch and a person reviews the diff, iterates and decides when to create the pull request, which then passes GitHub's own branch protection and review controls; managed settings files control agent command authorization across Copilot clients, and enterprise policy decides where the agent may run at all.

Sourcedocs.github.com about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

Security, Identity & Governance Full

Enterprises set four agent policy states, including enabled for dynamic groups of organizations, manage custom agents at enterprise level through AI Controls or REST endpoints, restrict MCP servers and control plugin installs through managed settings. GitHub Copilot Business and Enterprise are covered by SOC 2 Type II reports available on the GitHub Enterprise Trust Center.

Sourcedocs.github.com concepts/agents/enterprise-management and github.blog/changelogread 2026-09-29

Observability & Auditability Full

The enterprise audit log records agent actions such as pull_request.create with actor_is_agent, the agent_session_id and the initiating user, filterable with actor:Copilot over 180 days and streamable to external destinations (public preview), and AI Controls lists and filters agent sessions across the enterprise. The audit log does not include client session data, so prompts sent locally are not captured and a custom hook is needed to log CLI events.

Sourcedocs.github.com agentic-audit-log-events and concepts/agents/enterprise-managementread 2026-09-29

Memory & State Persistence Full

Copilot Memory stores repository facts and user preferences that Copilot writes from users' work, scoped to the repository or the user, validated against the current branch before use, deleted after 28 days unused, and reviewable and deletable by repository owners and by organization or enterprise admins; the cloud agent, code review, the CLI and agentic autofix use it. Copilot Memory is in public preview on all paid plans.

Sourcedocs.github.com concepts/agents/copilot-memoryread 2026-09-29

Deployment & Data Residency Full

Copilot with data residency is offered in the United States and the European Union: requests route to model endpoints in the enterprise's region, code, prompts and responses stay in region during inference, and Copilot logs and telemetry are stored in region.

Sourcedocs.github.com github-copilot-with-data-residencyread 2026-09-29

Prebuilt Agents, Templates & Packs Full

Copilot ships several agents that teams can adopt one at a time, the cloud agent, Copilot code review, agentic autofix and the Copilot CLI, and third party coding agents from Anthropic and OpenAI (Claude, Codex) can be used alongside it in public preview. Custom agents, skills and hooks let teams add their own.

Sourcedocs.github.com concepts/agents/copilot-memory, about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

Triggers & Channel Coverage Full

An automation runs the cloud agent on a schedule or in response to events such as an issue being opened, with no person starting it; beyond that the agent is assigned issues, answers @copilot mentions in pull requests and takes tasks from Slack, Teams, Jira, Linear, Azure Boards, the agents panel and VS Code.

Sourcedocs.github.com about-coding-agentread 2026-09-29

Model Flexibility & Routing Full

Paid users select among models from OpenAI, Anthropic, Google, xAI, Moonshot AI and Microsoft, with an optional one million token context, or use auto model selection, and Business and Enterprise admins decide by policy which models are enabled; Free and Student plans get auto selection only.

Sourcedocs.github.com reference/ai-models/supported-modelsread 2026-09-29

APIs, SDKs & MCP Extensibility Full

The Copilot SDK exposes the agent loop, custom agents and cloud and remote sessions with server to server tokens, and REST endpoints manage custom agents at enterprise level, beside MCP and the CLI.

Sourcedocs.github.com get-started/features and concepts/agents/enterprise-managementread 2026-09-29

Testing, Debugging & Optimization Partial

The cloud agent runs the project's tests, code review checks the customer's changes, admins can pilot a feature or model with a group of users, and agent sessions support troubleshooting. Those check the customer's code or trial adoption, and no tools for testing or scoring the agent's own behavior are described.

Sourcedocs.github.com get-started/features and about-coding-agentread 2026-09-29

Browser & Computer Use Full

The Playwright MCP server is enabled by default for the cloud agent, so the agent drives a browser in its own environment to open, interact with and screenshot the web app it is building, with the browser supplied by GitHub. The browser steps themselves are not described in detail.

Sourcedocs.github.com about-coding-agentread 2026-09-29

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·Human approval / guardrailsPartially Verified

Copilot CLI 1.0.111 adds regular expression support to enterprise managed Shell, Bash and PowerShell permission rules, so administrators can allow or deny families of agent commands by pattern. The same release adds --host-allow-session-creation, which lets remote clients create sessions on a CLI host for one launch without changing saved settings.

Bears on: Human approval / guardrails

View source
·Deployment / data residencyVerified

The GitHub Copilot app now works with GitHub Enterprise Server: users add a GHES account under Settings > Accounts and work with remote repositories, issues and pull requests on their self hosted instance. The feature moves from opt in preview to general availability in Copilot app 1.2.0 and later; cloud sessions are not available for GHES.

Bears on: Deployment / data residency

View source
·Agent capabilityPartially Verified

Copilot CLI 1.0.108 adds /index commands and turns on managed shared tgrep indexing by default for eligible repositories, so the agent searches large codebases through a trigram index instead of scanning files on each query. The same release adds Windows enumerate only directory grants for the CLI sandbox.

Bears on: Agent capability

View source
View all 35 GitHub Copilot updates →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

Pro from $10 a month, with a free tier. Business is $19 and Enterprise $39 per seat a month.

Hybrid. Each plan or seat carries a flat monthly price and an included allowance of GitHub AI Credits, and usage beyond the allowance costs $0.01 a credit.

Free tier

Included quota

The Free plan includes 2,000 inline suggestions a month and limited chat and agent use. Pro at $10 includes 1,500 AI Credits, Pro+ at $39 includes 7,000 and Max at $100 includes 20,000. Business at $19 per seat includes 1,900 credits per user, and Enterprise at $39 per seat includes 3,900 per user.

What is public

Every plan is published with its credit allowance. Free is $0 with 2,000 inline suggestions a month and limited chat and agent use, and Student is free. Pro is $10 a month with 1,500 AI Credits (1,000 base plus 500 flex), Pro+ $39 with 7,000 and Max $100 with 20,000. Business is $19 per granted seat a month with 1,900 credits per user, and Enterprise $39 per granted seat with 3,900 per user. Inline suggestions are unlimited on paid plans.

Billing mechanics

Each seat or plan has a monthly price plus an included GitHub AI Credits allowance that chat, agent and premium model use draw down. Additional credits cost $0.01 each against a dollar budget the user sets. On Business and Enterprise, admins decide whether paid usage beyond the allowance is allowed.

Cost watchouts

Agent and premium model use draws AI Credits at $0.01 each beyond the included allowance.

Variable cost rationale

GitHub AI Credits meter chat, agent and premium model use. Each plan or seat includes a monthly allowance, from 1,500 credits on Pro to 3,900 per user on Enterprise, and consumption varies by model and task, so heavy agent work draws it down fastest. Beyond the allowance, credits cost $0.01 each. The plan or seat price itself is flat, and inline suggestions are unlimited on paid plans. Extra credits are spent only against a dollar budget the user sets, and on Business and Enterprise admins decide whether paid usage beyond the allowance is allowed at all.

Additional watchouts

Agent and premium model use draws AI Credits, so heavy agent users can exceed the included allowance and pay per credit on top of the plan price unless a budget or admin policy stops it.

Overage / add-ons

Agent and premium model use beyond the included AI Credits allowance is billed as usage based overage at $0.01 a credit, or capped by budgets and admin settings.

Sales call required

No, self serve available

Free / trial

Free plan with 2,000 inline suggestions a month and limited chat and agent use. No trial is published.

Lowest paid plan

Pro at $10 per month, with 1,500 AI Credits a month

Commercial notes

Individual plans are bought self serve. Business and Enterprise are bought per granted seat through a GitHub organization or enterprise account.

Key ambiguities

Effective cost for agent work depends on credit consumption by model and task, beyond the published plan or seat price.

Cancellation / refund

Individual plans are self serve and billed monthly, and Business and Enterprise bill per granted seat. Extra usage is charged only against a dollar budget the user sets.

Missing data

How many credits a given task or model consumes varies and is not a single published figure.

Agentic Index verified 2026-10-25

Alternatives to GitHub Copilot

The closest documented capability profiles to GitHub Copilot among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.