Features

Native AI across the workbench — not a bolt-on chat tab.

AI modes

Ask for answers, Agent for execution, Plan before you code.

Fast Q&A on code and concepts without touching the repo.

Tools for files, search, and terminal — with Keep, Undo, and Review on changes.

Structured planning pass before implementation — fewer wrong turns.

Every workspace root, not just the active editor tab.

Agent resolves paths across all folders in your workspace.

Attach terminal output and files so the model sees real state.

See what changed before you commit to it.

Per-file diffs with Keep all, Undo all, or Review in the editor.

Terminal runs from the agent — dismissible when you are done.

Stay in flow when conversations grow.

Summarizes older messages so context stays within model limits — send is rarely blocked.

Status bar shows estimated usage; manual /compact when you want control.

Sensible scaffolds for Next.js, Flutter, and more — injected into Agent prompts.

Shipped JSON, optional local override, or team-hosted playbook URL.

Gateway-backed OpenAI and Anthropic with rate-limit handling.

Validates requests, repairs tool history, and paces TPM before provider 429s.