The datasheet for every AI agent

SearchSearch agents (press slash)Submit an agent

Claude Code

Claim this listing

Coding agents

Visit Claude Code Compare

Anthropic’s terminal-native coding agent with full-repository context. Included from the $17/month Claude Pro plan, or billed per token through the API.

Screenshot of Claude CodeVerified · theagentsindex.com
From
Free
Pricing model
freemium
Free tier
Yes
Deployment
Self-host
Interface
CLI
Open source
No
Public API
Yes
Model / LLM
Claude Sonnet 5 and Claude Opus…

Our verdict

Claude Code is the pick for developers who want an agent that lives in the terminal and composes with real engineering workflows, scripts, CI pipelines and headless automation, rather than a bolted-on chat panel.

Its reasoning holds up on genuinely multi-step tasks across a full repository, and it asks permission on sensitive actions instead of working blind. There is no graphical editor, so anyone who wants point-and-click review will feel the gap, and usage-based cost on long autonomous runs is worth watching.

It is the strongest option for CI-driven or command-line-first teams, and a weaker fit for developers who want a GUI-first experience. Claude Code hit $1B in run-rate revenue within six months of launch, and Anthropic, backed by a $65B Series H at a $965B valuation, is investing directly in its toolchain after acquiring the Bun JavaScript runtime Claude Code ships as an executable.

The tradeoff of that single-vendor stack is that Claude Code is tied exclusively to Claude models, with no built-in switch to GPT or Gemini the way some editor-based rivals allow.

What is Claude Code?

Claude Code is Anthropic’s agentic coding tool that runs in the terminal and through IDE integrations. It gives Claude direct, permissioned access to a codebase so it can read, edit, run commands and complete multi-step engineering tasks with the model’s reasoning.

It hit $1B in run-rate revenue within six months of its public launch, and Anthropic, now backed by a $65B Series H at a $965B valuation, is investing directly in its toolchain after acquiring the Bun JavaScript runtime Claude Code ships as a compiled executable. Claude Sonnet 5 is available inside Claude Code alongside Opus.

What does Claude Code do?

From the command line, you give Claude Code a task. It explores the repository, makes a plan, edits files, runs tests and iterates, asking permission for sensitive actions. It fits scripting and CI as well as interactive use, and is included on a Claude Pro, Max, Team or Enterprise plan, or billed pay-per-token via the Anthropic API.

How Claude Code works

  1. Install the Claude Code CLI on macOS, Linux or Windows, or add the VS Code or JetBrains extension.
  2. From the command line, give Claude Code a task in natural language.
  3. It explores the repository, forms a plan, edits files across the codebase, and runs tests or builds, asking permission for sensitive actions.
  4. Authenticate with a Claude Pro or Max subscription, or an Anthropic API key, and Claude Code usage draws from that plan or token balance.

Key features

Terminal-native agent
Runs where developers work, the shell, and composes with scripts and CI pipelines.
Full-repo context and tools
Reads the whole codebase and runs real commands (tests, builds) with permission.
Strong reasoning
Built on Anthropic’s Claude models for multi-step engineering tasks.
Multi-surface IDE and web support
Terminal plus VS Code and JetBrains extensions, web app, iOS and Android, and GitHub Actions integration.

What are Claude Code's use cases?

Autonomous multi-step tasks
Hand a well-scoped change to Claude Code and let it plan, edit and verify.
Scripted and CI automation
Drive it headless in pipelines for repetitive engineering work.
IDE-assisted pair coding
Run it from VS Code or JetBrains with the same terminal engine behind it.

Who is Claude Code for?

  • Developers and teams who want a terminal-native, scriptable agent that composes with CI and real engineering workflows
  • Engineers handing off well-scoped, autonomous multi-step tasks who want strong reasoning over a full repository
  • Teams already on a Claude Pro or Max subscription who want the agent included rather than billed separately

Not forDevelopers 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.

What does Claude Code integrate with?

  • Terminal / shell and CI pipelines
  • VS Code and JetBrains IDE extensions
  • GitHub Actions
  • MCP servers and external tools
  • Claude for Slack, iOS and Android apps
  • Anthropic API and Claude Pro, Max, Team, Enterprise billing

Why use Claude Code?

  1. Terminal-native, composes with existing developer workflows and CI.
  2. Strong reasoning for genuinely multi-step tasks, not just completions.
  3. Included from the $17/month Pro plan, so heavy users are not paying a separate Claude Code bill.

What are Claude Code's pros and cons?

What's great

  • Terminal-native and scriptable, fits real engineering workflows and CI.
  • Strong multi-step reasoning over a whole repository.
  • Included from the $17/month Pro plan, no need to pay for Max just to use it.
  • Backed by real scale and continued investment. Claude Code hit $1B run-rate revenue six months after launch, and Anthropic raised a $65B Series H in May 2026 at a $965B valuation, naming Claude Code directly as a product it is expanding capacity for.

Watch-outs

  • Terminal-first, no full graphical editor for those who want one.
  • Usage-based cost can add up on large, long-running tasks, and heavy users still get pushed onto Max ($100/month) for meaningfully more headroom.
  • Locked to Anthropic’s own Claude models. Unlike Cursor or GitHub Copilot, there is no built-in option to switch to GPT or Gemini.
  • Terminal-first. There is no full graphical editor for those who prefer point-and-click.
  • Usage-based billing can climb on large, long-running autonomous tasks.
  • Single-vendor stack. You cannot route to non-Anthropic models from inside Claude Code.

Claude Code pricing

USD. Pro is $17/month billed annually or $20/month billed monthly. Max starts at $100/month. A Free tier exists for general Claude use, with Claude Code access governed by plan quotas.

  • Free

    Free

    • Claude on web, iOS, Android and desktop
    • Code generation and visualisation
    • Claude Code access within plan quotas

  • Pro

    $17 / month (annual) or $20 monthly

    • More usage than Free
    • Includes Claude Code, Claude Cowork, Claude Design and Claude Science
    • Access to Research and more Claude models
    • Claude for Microsoft 365

  • Max

    $100 / month

    • 5x to 20x more usage than Pro
    • Higher output limits, priority access

  • API usage

    Usage-based (pay-per-token)

    • Pay per token through the Anthropic API. No subscription required.
    • No subscription required.

See current pricing on claude.com ↗Compare Claude Code alternatives →

Frequently asked questions

How is Claude Code billed?
It is included on a Claude Pro subscription ($17/month billed annually, $20/month billed monthly) or a Max subscription (from $100/month, with 5x to 20x more usage than Pro). The Free tier exposes Claude Code within plan quotas. You can also skip the subscription and pay per token directly through the Anthropic API.
Can it run without a human watching?
Yes. It is scriptable and fits CI, but it asks permission for sensitive actions by default, so you choose how autonomous each run is.
Does Claude Code work in an IDE?
Yes. It is terminal-first but also ships IDE extensions for VS Code and JetBrains, so you can drive it from the editor while it still composes with scripts and CI.
How much revenue does Claude Code generate, and how stable is the company behind it?
Claude Code passed $1 billion in run-rate revenue in November 2025, just six months after its public launch. Anthropic, its maker, raised a $65 billion Series H in May 2026 at a $965 billion post-money valuation, with total run-rate revenue crossing $47 billion, and in December 2025 it acquired the Bun JavaScript runtime that Claude Code ships as a compiled executable, keeping Bun open-source and MIT-licensed.

Claude Code alternatives

  • OpenAI Codex CLI

    No new bill if you already pay for ChatGPT Plus or above, versus Claude Code's standalone $17/month-minimum Pro subscription, though OpenAI's own rate card puts typical real-world Codex CLI cost at $100-200/developer/month once you are a regular user.

  • Aider

    A free, open-source, bring-your-own-model terminal harness where every AI edit lands as its own git commit, for developers who want a fully auditable trail and zero vendor lock-in instead of Claude Code's deeper single-vendor reasoning.

  • Devin Desktop (formerly Windsurf)

    Full IDE rather than a terminal agent, with the open Agent Client Protocol letting you run Claude Code, Codex and Devin side by side in one editor.

  • Compare the whole category

    Every agent in Coding agents, side by side on the same fields.

Visit Claude CodeOpens the vendor's own siteCompare Claude CodeSide by side with the categorySee alternativesOther options worth weighing

Anything to add?

This page is researched and re-verified by our editors — but the people who actually use Claude Code know things we cannot see from the outside.

Write a reviewUsed Claude Code? Your experience helps the next buyer decide.
Get a quote from Claude CodeTell us what you need and we make the introduction.
Get weekly Coding agents updates

New agents and fresh verdicts. One short email, every week. One-click unsubscribe.

Advertise

Reach buyers mid-decision. Put your brand in front of them — sponsor slots are open to any advertiser (see the content policy); listed agents can go Featured at the top of their category.

Featured — top of your category →Sponsor this page →

The evidence

Facts re-verified

How we checked this

Strongest command-line-first agent, deep reasoning over a whole repo, with usage-based cost the main thing to watch on long autonomous runs.

Tags

APIAutonomousClaude

What changed, and what we read (2 updates)

  1. AlternativesBest forConsFaq itemsFree trial daysHow it worksIntegrationsKey featuresLimitationsPricingProsTaglineUse casesVerdictWhat isWhat it doesWhy use

    Read claude.com (official), claude.com (official), anthropic.com (official), anthropic.com (official), anthropic.com (official)

  2. Tier priority

Reviewed by The Agents Index Editorial, Research desk.

Advertise

Reach buyers mid-decision. Put your brand in front of them — sponsor slots are open to any advertiser (see the content policy); listed agents can go Featured at the top of their category.

Featured — top of your category →Sponsor this page →

Advertise

Reach buyers mid-decision. Put your brand in front of them — sponsor slots are open to any advertiser (see the content policy); listed agents can go Featured at the top of their category.

Featured — top of your category →Sponsor this page →

Your agent, listed

Built an AI agent or agentic tool? Get it researched, quality-gated and listed.

Submit it free