Compare AI tools

	Claude Code S	Elicit S	Fathom S	ChatGPT Operator B
Tagline	Anthropic's CLI agent. Opus-powered, operates on your repo directly.	AI research assistant for academic literature.	Meeting notes, free forever for individuals.	OpenAI's browser agent. Clicks and types on websites for you.
Category	coding	research	meeting	agents
Pricing	Part of Claude Pro/Max/Team plans	Free + $12-$42/mo	Free for individuals + $15-$29/user/mo teams	Included with ChatGPT Pro $200/mo
Best for	Developers who want an agent, not autocomplete. Large refactors, tests, docs.	Grad students, researchers, anyone doing literature reviews.	Solo operators, freelancers, small teams on a budget.	Power users willing to pay $200/mo for a browser bot.
Strengths	Runs locally, edits your actual files Strong on large codebases with 1M context Great at multi-step tasks	Searches 125M+ papers Extracts + synthesizes findings across papers Systematic review workflow	Unlimited free tier for solo use Strong summaries + action items Works in Zoom, Meet, Teams	Actually uses websites — fills forms, clicks, checks out Built into ChatGPT Good for repetitive web tasks
Weaknesses	Terminal-based — learning curve Can't be used without Claude subscription	Academic-only Can hallucinate citations — verify everything	Bot-joining model Team features gated	Slow vs doing it yourself Breaks on complex auth flows $200/mo gate
Kai's verdict	S-tier if you live in the terminal. Different shape than Cursor — complementary, not replacement.	S-tier for academic research. Nothing else comes close for systematic reviews.	S-tier for solo + free. The best free option, hands down.	B-tier. Still early. Manus is more flexible for less money.
Link	Open →	Open →	Open →	Open →