Coding agents
Claude Code
Anthropic’s agentic coding tool, available in the terminal, desktop, web, and as IDE extensions for VS Code and JetBrains.
- Category
- Coding agents
- Pricing
- Subscription
- Runs
- Hosted or self-hosted
- Interface
- CLI, Desktop app, Web, IDE extension
- Source
- Proprietary
What Claude Code is
Claude Code is Anthropic's own agent harness: it searches and reads the repository, edits across files, runs commands and tests, and reacts to what they return. It runs in the terminal, in desktop and web apps, and as VS Code and JetBrains extensions, with the same agent behind each. The underlying harness also ships as the Claude Agent SDK for building on directly.
Best for
Substantial multi-file work — refactors, features, and debugging — where the agent needs to run tests and iterate rather than produce one diff.
Consider something else if
It runs Claude models specifically, so it is not the tool for pointing an agent at an arbitrary provider or a local model.
Claude Code alternatives
The closest options in coding agents, on the axes that actually separate them.
| Tool | Best for | Pricing | Runs |
|---|---|---|---|
| Claude Code | Substantial multi-file work — refactors, features, and debugging — where the agent needs to run tests and iterate rather than produce one diff. | Subscription | Hosted or self-hosted |
| Cursor | Developers who want completion, chat, and agentic editing in one editor with no assembly required. | Subscription | Hosted |
| Aideropen source | Terminal-first developers who want an agent that is model-agnostic and whose every change is a reviewable commit. | Open source | Runs locally |
| Clineopen source | Working inside VS Code with visible, approvable steps rather than handing over autonomy. | Open source | Runs locally |
| OpenHandsopen source | Autonomous runs where you want isolation by construction, and for building on an agent loop you can modify. | Open source | Hosted or self-hosted |
Choosing within coding agents
Where it runs
Terminal, inside an editor, or in a sandbox in the cloud. Terminal and editor agents act with your local credentials and can run anything you can. Sandboxed agents are safer by construction and slower to set up.
How it asks permission
Approve-every-command is safe and tiring; full autonomy is fast until it runs a migration you did not want. The useful question is whether the granularity is configurable per tool or per command, not whether the agent is "safe".
Questions
What is Claude Code?
Claude Code is Anthropic's own agent harness: it searches and reads the repository, edits across files, runs commands and tests, and reacts to what they return. It runs in the terminal, in desktop and web apps, and as VS Code and JetBrains extensions, with the same agent behind each. The underlying harness also ships as the Claude Agent SDK for building on directly. It is a commercial product and hosted or self-hosted.
What are the alternatives to Claude Code?
The closest alternatives are Cursor, Aider, Cline, OpenHands. They sit in the same category — coding agents — and differ mainly on hosting model, pricing shape, and how much they abstract away.
Is Claude Code the right choice?
Substantial multi-file work — refactors, features, and debugging — where the agent needs to run tests and iterate rather than produce one diff. The main caveat: It runs Claude models specifically, so it is not the tool for pointing an agent at an arbitrary provider or a local model.
Whatever you build on, the model is the line item that scales. See what each one costs per million tokens, or price your own workload.