AI tools that actually speed up your coding

Most AI coding demos work because the project is empty. The interesting question is what happens in a repository with ten years of history and no tests.

These are the tools that hold up there, sorted by the job they do best.

Agent in the terminal

Claude Code

Reads the repository, runs commands and makes multi-file changes; the strongest option for real refactors.

claude.com/claude-code

Autocomplete

GitHub Copilot

Still the best inline completion, and it is where most teams already have a licence.

github.com/features/copilot

Editor

Cursor

VS Code rebuilt around chat and multi-file edits, with the extensions you already use.

cursor.com

Open source

Continue

Brings an assistant into VS Code or JetBrains using whichever model you choose, including local ones.

continue.dev

Terminal and git

Aider

Pairs with you from the command line and commits each change separately, which makes review easy.

aider.chat

Local models

Ollama

Runs models on your own machine when the code cannot leave the building.

ollama.com

Editor

Zed

A genuinely fast editor with AI and collaboration built in rather than bolted on.

zed.dev

The tools are not the bottleneck any more: reviewing what they produce is. Keep the diffs small enough to actually read.

Need it built, not just chosen?

Web apps, APIs, infrastructure and interfaces. Freelance from Barcelona, working with clients anywhere.

Get in touch


Comments

Leave a Reply

Your email address will not be published. Required fields are marked *