Claude Code
Hard, multi-step coding work in the terminal when you want the highest benchmark scores.
Agents and editors that read, write, test and ship code in your repo.
| Tool | Free tier | Best for |
|---|---|---|
| Claude Code | No | Hard, multi-step coding work in the terminal when you want the highest benchmark scores. |
| OpenAI Codex | Yes | Getting strong agentic coding for the lowest cost per task, starting free with a ChatGPT account. |
| Cursor | Yes | An AI-first code editor for everyday work, with local and cloud agents. |
| GitHub Copilot | Yes | Teams already on GitHub who want agent mode, cloud agents and code review in their existing IDE. |
| Devin (Desktop & Cloud) | Yes | Managing several local and cloud coding agents from one IDE, including third-party agents. |
| Google Antigravity | Yes | Developers on Google's stack who want a free agent-first IDE and CLI powered by Gemini. |
| Kiro | Yes | Structured, spec-first agentic development, especially for AWS-centric teams. |
| Augment Code | Unknown | Small teams working in large codebases who want one flat team price. |
| JetBrains Junie | Yes | Developers who live in IntelliJ, PyCharm, WebStorm and other JetBrains IDEs. |
| Zed | Yes | A very fast editor with built-in AI, where you pay only for the tokens you use. |
| Amp | Yes | Agents that keep working on remote machines ("orbs") after you close your laptop, using models you already pay for. |
| Cline | Yes | An open-source agent in your editor where you control the model and pay only for inference. |
| Aider | Yes | Terminal pair programming with automatic git commits and any LLM, including local models. |
| OpenCode | Yes | Trying a capable open-source terminal agent for $0, with free models and no account. |
| Goose | Yes | An extensible open-source agent that can install, execute, edit and test with any LLM. |
Hard, multi-step coding work in the terminal when you want the highest benchmark scores.
Getting strong agentic coding for the lowest cost per task, starting free with a ChatGPT account.
An AI-first code editor for everyday work, with local and cloud agents.
Teams already on GitHub who want agent mode, cloud agents and code review in their existing IDE.
Managing several local and cloud coding agents from one IDE, including third-party agents.
Developers on Google's stack who want a free agent-first IDE and CLI powered by Gemini.
Structured, spec-first agentic development, especially for AWS-centric teams.
Small teams working in large codebases who want one flat team price.
Developers who live in IntelliJ, PyCharm, WebStorm and other JetBrains IDEs.
A very fast editor with built-in AI, where you pay only for the tokens you use.
Agents that keep working on remote machines ("orbs") after you close your laptop, using models you already pay for.
An open-source agent in your editor where you control the model and pay only for inference.
Terminal pair programming with automatic git commits and any LLM, including local models.
Trying a capable open-source terminal agent for $0, with free models and no account.
An extensible open-source agent that can install, execute, edit and test with any LLM.