Features
Three interaction modes: Plan (read-only), Edit (approval), Auto (autonomous)
Live task panel with progress icons, elapsed time, token deltas
Image understanding (PNG/JPG/WebP/GIF/BMP ≤5 MB, local paths)
14 terminal themes with live preview (Ctrl+T)
Paste collapse for clean scrollback
Type-ahead queue for queuing prompts
Auto-compaction nudges at ~80% context usage
/compact command to summarize older turns
Streaming reasoning toggle (/reasoning or Ctrl-R)
Session persistence with /resume and paginated picker
Smart permissions: session-allow by first token, unified diff for write/edit
MCP server integration (local stdio or remote SSE)
Built-in tools: read, write, edit, bash, glob, grep, web_fetch, tasks_set
One-shot mode: kimiflare -p "command"
Visual screen editor with infinite canvas
AI agents: Claude, GPT, Gemini, Qwen 3.7 Max, Claude Opus 4.8, Gemini 3.5 Flash
BYO API keys for OpenAI, Anthropic, OpenRouter on any plan
Live preview on device via QR code
Built-in code editor for pixel-level control
One-click publishing to web, iOS, Android
Full version control with rollback
Shared task board for organizing work
Team collaboration with roles and permissions
REST API integration with one-click setup (Webflow, Shopify, Xano, Supabase)
Supabase backend (database, auth, storage) in open beta
Theme and typography editing with Google Fonts picker
MCP integrations: Cloudflare, HighLevel
Exportable source code with full GitHub history
Expert services: scoping, design, backend, troubleshooting
