Which AI code editor should I use?

+ Startup and typing latency are far lower than any Electron-based AI editor.
− Extension ecosystem is small compared with VS Code and Windows support only arrived in 2025.

+ Tab autocomplete predicts multi-line edits across files better than any competitor.
− Usage-based pricing changes and request limits on Pro have repeatedly frustrated heavy users.

+ Deepest GitHub integration: assign an issue to Copilot and it opens a PR.
− Completions and agent lag behind Cursor and Claude Code in quality despite more models being offered.

+ Works with local Ollama models or any API, with fully customisable config.
− Setup is more fiddly than Copilot and autocomplete quality depends entirely on the model you choose.

+ Uses the IDE's own semantic index and refactorings, so edits respect project structure.
− Quota-based AI credits run out quickly on the lower tiers.

+ Cascade keeps context of what you just did in the editor and terminal without being told.
− Ownership turmoil in 2025 (OpenAI deal collapse, Google, then Cognition) caused model-access gaps.

+ Context retrieval holds up on monorepos with hundreds of thousands of files.
− Pricing moved to credits and sits well above Copilot for individual developers.

+ Spec-driven workflow produces requirements and design docs before code, which keeps agents on track.
− Waitlists and tight free-tier limits made it hard to actually use after launch.

+ Generous free access to Claude and GPT models compared with other editors.
− ByteDance ownership raises data-residency concerns and the free tier queues under load.

+ Goes from prompt to a deployed Firebase-backed app without leaving the browser.
− The App Prototyping agent is Next.js-centric and the cloud IDE can feel sluggish.

+ Air-gapped and on-prem deployment with models not trained on copyleft code.
− Completion quality trails Copilot and Cursor for general use.