Compare AI tools

	Claude Code S	Windsurf A	ChatGPT Operator B	Bolt.new (StackBlitz) A
Tagline	Anthropic's CLI agent. Opus-powered, operates on your repo directly.	Codeium's agentic IDE. Cascade agent + strong free tier.	OpenAI's browser agent. Clicks and types on websites for you.	Prompt to deployed full-stack app in the browser.
Category	coding	coding	agents	coding
Pricing	Part of Claude Pro/Max/Team plans	Free + $15/mo Pro	Included with ChatGPT Pro $200/mo	Free + $20-$200/mo
Best for	Developers who want an agent, not autocomplete. Large refactors, tests, docs.	Developers who want Cursor-like power for less money.	Power users willing to pay $200/mo for a browser bot.	PMs, founders, non-devs shipping MVPs.
Strengths	Runs locally, edits your actual files Strong on large codebases with 1M context Great at multi-step tasks	Cheaper than Cursor Cascade agent for multi-file tasks Solid free tier	Actually uses websites — fills forms, clicks, checks out Built into ChatGPT Good for repetitive web tasks	Full-stack generation + live preview Deploy to Netlify in one click Works in-browser — no install
Weaknesses	Terminal-based — learning curve Can't be used without Claude subscription	Smaller community Model selection more limited	Slow vs doing it yourself Breaks on complex auth flows $200/mo gate	Quality ceiling for complex apps Can get into loops for non-trivial bugs
Kai's verdict	S-tier if you live in the terminal. Different shape than Cursor — complementary, not replacement.	A-tier. Close second to Cursor. If $5/mo matters, start here.	B-tier. Still early. Manus is more flexible for less money.	A-tier. Best for fast prototypes. Competitive with Lovable — try both.
Link	Open →	Open →	Open →	Open →