Compare AI tools

	Lex A	Claude Code S	OpenRouter S	Granola S
Tagline	Google Docs with an AI collaborator baked in.	Anthropic's CLI agent. Opus-powered, operates on your repo directly.	One API, every model. Pay-as-you-go, no subscriptions.	Meeting notes that don't suck. Runs locally, no bot joins.
Category	Writing	Coding	Dev Platform	Meetings
Pricing	Free + $12/mo	Part of Claude Pro/Max/Team plans	Pay per token — model-dependent	Free + $18/mo
Best for	Essays, long-form drafts, thinking on the page.	Developers who want an agent, not autocomplete. Large refactors, tests, docs.	Developers experimenting across models. Apps that want fallback logic.	Founders, execs, consultants who live in calls.
Strengths	Clean writing UX — distraction-free +++ prompt triggers AI help Collaboration + AI feedback together	Runs locally, edits your actual files Strong on large codebases with 1M context Great at multi-step tasks	300+ models from one endpoint Automatic fallbacks between providers No subscription — just pay what you use	No bot in the call — runs on your Mac Strong templates Fast summaries
Weaknesses	Less feature-rich than Google Docs AI ceiling below dedicated tools	Terminal-based — learning curve Can't be used without Claude subscription	Slight markup over direct API Some provider features not exposed	Mac-only Single-user by design
Kai's verdict	A-tier. Beautiful UX. The writing app I'd pick if I only wrote long-form.	S-tier if you live in the terminal. Different shape than Cursor — complementary, not replacement.	S-tier for model-shopping. I use this for every prototype before committing.	S-tier. Category-defining UX. If you take notes in meetings, switch this week.
Link	Open →	Open →	Open →	Open →