Coding agents
Aider
Terminal pair programmer that edits files in your git repo and commits as it goes.
- Category
- Coding agents
- Pricing
- Open source
- Runs
- Runs locally
- Languages
- Python
- Interface
- CLI
- Source
- Open source
What Aider is
Aider runs in the terminal against your git checkout and treats version control as the interface: each change lands as a commit, so reviewing and undoing agent work uses tools you already have. It builds a repository map to give the model structure without loading everything, and works with whichever provider you supply a key for.
Best for
Terminal-first developers who want an agent that is model-agnostic and whose every change is a reviewable commit.
Consider something else if
You bring your own API key, so token cost is yours directly — and agentic loops consume a lot of them.
Aider alternatives
The closest options in coding agents, on the axes that actually separate them.
| Tool | Best for | Pricing | Runs |
|---|---|---|---|
| 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 |
| 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 |
| 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 |
| Cursor | Developers who want completion, chat, and agentic editing in one editor with no assembly required. | Subscription | 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 Aider?
Aider runs in the terminal against your git checkout and treats version control as the interface: each change lands as a commit, so reviewing and undoing agent work uses tools you already have. It builds a repository map to give the model structure without loading everything, and works with whichever provider you supply a key for. It is open source and runs locally.
What are the alternatives to Aider?
The closest alternatives are Claude Code, Cline, OpenHands, Cursor. They sit in the same category — coding agents — and differ mainly on hosting model, pricing shape, and how much they abstract away.
Is Aider the right choice?
Terminal-first developers who want an agent that is model-agnostic and whose every change is a reviewable commit. The main caveat: You bring your own API key, so token cost is yours directly — and agentic loops consume a lot of them.
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.