Most agents think the same on every prompt. Finch 1.6.1 thinks harder when the work is actually hard. • Professional thinking mode: a deeper reasoning chain for messy, multi-step work, not “max thinking” on every prompt • GLM 5.3 and GLM 5.3 Flash, and it won’t auto-select a model you can’t actually use • Skills from ~/.agents/skills, the shared path people are already putting agent skills in • Diffs and file preview now use Shiki. About 10x faster on big files • Session.suggest: when a turn ends, it proposes the next move instead of going quiet • Mini-apps get a Finder-style file picker, HTML preview, and a usage dashboard you can actually read If you run agents all day, this is the 1.6.1 that matters.

Grok Bot gave Grok a cloud computer. Finch 1.6.0 puts it on yours. Native xAI login, a side panel that keeps browser and diffs alive across sessions, DeepSeek vision at 1M context.

Finch 1.5.4 is here. 🔍 Mini tool search: search community mini tools right in the toolbox. Better keyword matching and cleaner results — finding one is no longer a scroll. 🔤 Custom fonts: set your own interface font and code font in Appearance. Make Finch look like yours. 🐣 Smoother onboarding: Finch now recommends and installs mini tools for you. ⚡ Cache hit rate: 99.4% → 99.9% on DeepSeek. We reordered prompt priority so your context actually stays cached — cheaper and faster.

Meet Finch 🐦 A desktop AI agent that actually lives on your machine — remembers your projects across sessions, speaks to 13+ model providers, and asks before it touches a single file. The app is free. Permanently.