Claude Code

Summary

Claude Code is Anthropic's agentic coding tool for developers. It reads a codebase, plans a change, edits files across it, runs commands and tests, and takes the work through to a commit and pull request.

Best for: Developers and teams who want a terminal-native, scriptable agent that composes with CI and real engineering workflows.
Not for: Developers who want a GUI-first, click-to-edit experience over a command line, or teams that want the option to switch between model providers rather than being tied to Anthropic’s own Claude models.

Captured 2026-09-08 · theagentsindex.com

From: $20/month$20 monthly · $17 billed annually
Free tier: NoAnthropic's $0 Claude plan does not include Claude Code: the pricing FAQ states 'Claude Code is included in all paid plans.' The cheapest way in is Pro at $17/month billed annually ($20 monthly), or pay-as-you-go API credits through a Console account.

Visit Claude Code Compare Find alternatives

What it does

Writes code: YesTakes a plain-language description and writes the change across multiple files, then verifies it.Describe what you want in plain language. Claude Code plans the approach, writes the code across multiple files, and verifies it works.code.claude.com/docs/en/overview
Debugs and fixes: YesTakes an error message or symptom, traces it through the repository, and implements the fix.Claude Code traces the issue through your codebase, identifies the root cause, and implements a fix.code.claude.com/docs/en/overview
Writes tests: YesWrites tests for untested code as a named use case, and runs them as part of the same task.writing tests for untested code, fixing lint errors across a project, resolving merge conflicts, updating dependencies, and writing release notescode.claude.com/docs/en/overview
Reviews code: YesThe /code-review command reviews a local diff on any plan; the managed GitHub PR reviewer is a research preview on Team and Enterprise.Code Review analyzes your GitHub pull requests and posts findings as inline comments on the lines of code where it found issues.code.claude.com/docs/en/code-review
Whole-codebase work: YesDynamic workflows run many subagents over a repository for audits and large migrations; the vendor's own example is a 500-file migration.A job outgrows a handful of subagents, or you want findings verified against each other: a codebase-wide audit, a 500-file migration, cross-checked…code.claude.com/docs/en/agents
Ships it: PartlyThe claimed workflow ends at a commit, branch and pull request; deployment is only whatever shell command Claude is allowed to run.integrates with GitHub, GitLab, and your command line tools to handle the entire workflow—reading issues, writing code, running tests, and submitting…claude.com/product/claude-code

How much it does unattended

Runs autonomously: YesAuto mode has a classifier approve tool calls instead of a person; routines and background sessions run unattended, including in the cloud.Auto-approves tool calls with background safety checks that verify actions align with your requestcode.claude.com/docs/en/permissions
Multi-agent: YesFour coordination styles: subagents, background agent view, agent teams with inter-agent messaging (experimental, off by default), and dynamic workflows.Subagents, agent view, agent teams, and dynamic workflows each parallelize work in a different way.code.claude.com/docs/en/agents
Agent permissions: YesStarts read-only and asks per action in Manual mode; allow/ask/deny rules, six permission modes, and a bash sandbox set the boundary.In Manual mode, Claude Code starts with read-only permissions. When Claude Code needs to edit files, run tests, or execute commands, it asks you firstcode.claude.com/docs/en/security

Which models it runs on

Claude: YesClaude is the only model family: Fable, Opus, Sonnet and Haiku aliases, resolved per provider.Uses the latest Opus model for complex reasoning taskscode.claude.com/docs/en/model-config
GPT: NoOn the first-party API the recognised model strings are aliases and names beginning claude-; the alias table lists only Claude families.any name that starts with claude-code.claude.com/docs/en/model-config
Open models: NoNo open-weight option: every documented provider path (Anthropic API, Bedrock, Google Cloud, Microsoft Foundry) serves Claude models only.any name that starts with claude-code.claude.com/docs/en/model-config
Model choice: PartlyYou choose the model and effort per session or per subagent, but only within Claude; admins can pin the allowlist.Enterprise administrators can use availableModels in managed or policy settings to restrict which models users can selectcode.claude.com/docs/en/model-config

Where you use it

In your editor: YesFirst-party extensions for VS Code (and Cursor) and JetBrains IDEs, with inline diffs and plan review.Native extensions for VS Code (+ Cursor, Devin Desktop) and JetBrains IDEs.claude.com/product/claude-code
On the command line: YesThe terminal CLI is the primary surface, installed by shell script, Homebrew, WinGet or Linux package managers.Super powerful terminal integration. Works with all your CLI tools alongside any IDE.claude.com/product/claude-code
In your pipeline: YesGitHub Actions and GitLab CI/CD run it in your own pipelines; a managed GitHub PR reviewer exists on Team and Enterprise.In CI, you can automate code review and issue triage with GitHub Actions or GitLab CI/CD.code.claude.com/docs/en/overview
In a browser: YesCloud sessions run from claude.ai/code in a desktop browser or the iOS and Android app, with no local install.Run Claude Code in your browser with no local setup.code.claude.com/docs/en/overview

Whose machine it runs on

Self-hosted: PartlyThe CLI executes on your own machine, and cloud sessions can run on your runners in public beta on Team and Enterprise; inference always goes to Anthropic or a cloud provider.Self-hosted environments are in public beta on Team and Enterprise plans and are off by default.code.claude.com/docs/en/self-hosted-env…
Open source: NoThe vendor's own repository carries an all-rights-reserved licence; the public repo holds plugins, docs and the issue tracker, not the CLI source.© Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service.github.com/anthropics/claude-code/blob/…

What it costs to run

How it meters: YesTwo meters: a per-seat usage allowance on subscription plans, or per-token billing on the Console and cloud providers.On Teams and Enterprise plans, usage draws from each member's seat allowance. On the Console and on cloud providers, usage is billed per token to…code.claude.com/docs/en/costs
Free tier: PartlySelf-serve with no sales call, but there is no free tier: the $0 Claude plan excludes Claude Code, so the entry point is a paid plan or API pay-as-you-go.Claude Code is included in all paid plans.claude.com/pricing
API access: YesThe Agent SDK exposes the same agent loop as a Python or TypeScript library, and claude -p with JSON output drives it from any language.the same tools, agent loop, and context management that power Claude Code, programmable in Python and TypeScriptcode.claude.com/docs/en/agent-sdk/overv…
MCP server: Yesclaude mcp serve exposes Claude Code as a stdio MCP server other clients connect to; it is also an MCP client for external servers.You can use Claude Code itself as an MCP server that other applications can connect tocode.claude.com/docs/en/mcp
Bring your own key: YesBring your own Anthropic API key, or your own cloud account via Amazon Bedrock, Google Cloud's Agent Platform or Microsoft Foundry; apiKeyHelper supports vault-issued tokens.if your organization uses Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, set the required environment variables before running…code.claude.com/docs/en/authentication

Buying it for a team

A company can buy it: YesTeam is self-serve for 2 to 150 seats; Enterprise is available self-serve or sales-assisted with central billing.For teams of 2 to 150claude.com/pricing
Seat model: YesPer seat with a floor of 2 and a ceiling of 150 on Team; Standard $20/seat/mo annual ($25 monthly), Premium $100 ($125), Enterprise $20/seat plus usage.Per seat / month if billed annually. $25 if billed monthly.claude.com/pricing
Pooled budget: NoEach member gets their own allowance on a rolling five-hour and weekly window; only usage-credit spend past it can be capped at org, group or member level.each member's Claude Code usage draws from a per-seat allowance that resets on a rolling five-hour window and a weekly windowcode.claude.com/docs/en/costs
Admin controls: YesManaged and server-managed settings pin permission rules, model allowlists, telemetry and login method, and local settings cannot override them.Security teams can configure managed permissions for what Claude Code is and is not allowed to do, which cannot be overwritten by local configuration.code.claude.com/docs/en/third-party-int…
Audit log: PartlyAudit logs are an Enterprise plan feature, alongside a compliance API; cloud sessions log every operation, and OpenTelemetry export works on any plan.claude.com/pricing
Single sign-on: PartlySSO ships on the business plans, not on individual Pro or Max; the vendor names no protocol, and SCIM is Enterprise-only.Single sign-on (SSO)claude.com/pricing

What happens to your code

Opt out of training: YesCommercial terms (Team, Enterprise, API, cloud providers) are no-training by default; Free, Pro and Max users toggle it in privacy settings.Anthropic does not train generative models using code or prompts sent to Claude Code under commercial terms, unless the customer has chosen to…code.claude.com/docs/en/data-usage
Data residency: PartlyUS-only inference is selectable on the Claude API and Claude Platform on AWS at a 1.1x rate; workspace storage geo is US only, and Bedrock or Google Cloud regions follow the endpoint.Inference runs only in US-based infrastructure.platform.claude.com/docs/en/manage-clau…
Getting out: Yes/export writes a readable transcript, transcripts sit locally as JSONL, and org analytics and spend reports export as CSV; prepaid usage credits mostly do not expire.Run /export to open a menu that lets you copy the current conversation to your clipboard or save it as a plain-text filecode.claude.com/docs/en/sessions
Certifications: YesSOC 2 Type 2 and ISO 27001 artefacts are published at the Trust Center; a HIPAA-ready offering and zero data retention are Enterprise options.Learn more and access resources (SOC 2 Type 2 report, ISO 27001 certificate, etc.) at Anthropic Trust Centercode.claude.com/docs/en/security

Checked 2026-09-02 · How we check

Alternatives

Codex CLI
OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell.
Aider
Open-source terminal AI pair programmer that edits files in your local git repo and commits the changes.
Devin Desktop
AI IDE with a Kanban command center for running local and cloud coding agents; the renamed Windsurf.

Filed under

APIAutonomousClaudeMulti-agent

Sources and updates

Repository2026-08-30

Stars: 143,445
Forks: 22,939
Last push: 2026-08-28

Coverage elsewhere3

Updates3

2026-09-02Capabilities · Free tier · Price · Terms
2026-08-31Capabilities · Free tier · Price · Terms
2026-08-22Alternatives · Summary · Tagline