The best ai code editors, according to hackers

9 ai code editors recommended in Hacker News comments over the past year, ranked by how many separate people recommend each one.

All ai code editors

CursorAn AI code editor praised for in-editor review of agent changes, strong tab completion and working well in existing codebases; critics flag privacy worries and rising costs.853recommend
Google AntigravityRecommended for its generous usage limits, including Claude models, and its multi-agent and browser automation, though many report bugs, sudden quota cuts and risky unsupervised commands.337recommend
WindsurfFast agentic AI code editor, a VSCode fork, praised for coding help and codebase context. Most common caveat: frequent pricing changes.42recommend
AWS KiroDevelopers like its spec-driven workflow for requirements and tasks, but critics say it struggles with larger epics and does not always follow specs.36recommend
JetBrains AirPeople like it as an agentic coding harness that works in the IDE with any agent, locally or remotely. Common caveat: no Claude subscription or other AI provider support.13recommend
ThinkRail by JetBrainsLiked for worktrees as the core unit and use of the Pi agent core. Most common caveat: critics call it a VS Code wrapper that is feature-incomplete.11recommend
Zed DeltaPeople recommend it for keeping context from agent conversations, with annotation and sharing features and a solid alpha experience. Critics question the value of the sharing focus and warn of lock-in.9recommend
Intent by Augment CodeRecommended for multi-agent, spec-driven coding that keeps the developer's understanding of the code intact. Caveats raised are its own credits system and a setup seen as overkill.5recommend
TraePeople recommend it for its interface, planning and one-shot task completion. Critics say plan credits were cut from $400 to $100.5recommend