Launched this week
Bibby AI
The AI co-author for research papers
212 followers
The AI co-author for research papers
212 followers
Researchers spend more time writing papers than doing research. Bibby is an AI co-author for researchers. Forget the writing grind. Bibby digs through literature, drafts, and refines your paper. It will also find you citations and tell you mistakes before reviewers do. Think of it as a friend who knows research inside out, is by you at 3 am, and is deeply familiar with your work. Bibby has 200M+ citations, 800+ journal templates and is trusted at Yale, MIT, Stanford and Cambridge.
Bibby AI
Hey Product Hunt! Community 👋
I'm Nilesh. I was a researcher at Yale University.
I calculated once how much time I spent that year not doing research.
Managing citations. Fixing compiler errors. Reformatting for a different journal. Emailing .tex files back and forth.
It was months.
Not hours. Months of a PhD that I will never get back. I did not want to lose my entire train of thought every single time.
That's why I built Bibby for the scientific community.
What it does:
✍️ Autocomplete that understands your paper as you write
🔁 Reword any sentence with one click
✅ Grammar and academic tone fixes, right where you're typing
🤖 Bibby Chat: an AI co-author that knows your entire paper and helps you draft, restructure, and think
📸 Snap a photo of any equation, get it formatted perfectly in seconds
📚 Add citations from 200M+ papers with one click, no copy-pasting
🔍 Deep research mode: finds sources, spots gaps in the literature, and traces full citation trails
📝 Writes your entire literature review with real cited references
📄 Generates your abstract from your full paper in seconds
📊 Describe your data in plain English, Bibby builds the table
✅ AI paper reviewer trained on top conference standards, NeurIPS, ICML, ICLR, CVPR
🔧 Catches writing and formatting errors in real-time and fixes them with one click
📄 Upload any PDF, Bibby reads and analyses it.
👥 Collaborate with your whole team in real-time, no conflicts, no versioning chaos
🔀 Sync with GitHub, with automatic commit messages handled for you
⏪ Full version history with visual diffs and one-click restore
📋 5,000+ publisher-approved templates including IEEE, Nature, APA, NeurIPS and ACM
🔐 Your research never trains our models. Ever.
Trusted at Yale, Harvard, Stanford, MIT, Oxford and others.
Built by a researcher, for researchers.
How many hours did you waste last month on something that had nothing to do with your actual research writing?
@nilesharnaiya How's Bibby handling interdisciplinary papers, like blending AI/marketing research with real-world case studies?
Bibby AI
@swati_paliwal Interdisciplinary is genuinely the hard part because most tools are trained to think in neat categories, but real research rarely works that way. Bibby handles cross-domain papers better than most, especially when it comes to tracing where a concept originated vs. where it got applied. But there is a lot of room for improvement and we are working towards perfecting it.
Really curious about the photo-to-equation feature. How well does it handle complex multi-line equations? And does it work well with matrices or piecewise functions?
Bibby AI
@arnol_fokam Great question! It handles all of the MLE and matrices for sure.
It even works with whiteboard photos, not just neat handwriting on paper. We've tested it pretty extensively on the messy stuff researchers actually write. Try it and let me know if you find an equation that breaks it, we'll fix it.
Kandid
Curious to know, what LLM is powering the autocomplete and reviewer? Is it a fine-tuned model or are
you using something like GPT/Claude with custom prompting?
Bibby AI
@pulkitgarg Great question! Bibby works with multiple LLMs, you can connect Gemini, Anthropic, or even run it locally with Ollama(Coming soon). The reviewer is trained on evaluation criteria from top conferences (NeurIPS, ICML, ICLR, CVPR), so it's not just generic AI feedback so it knows what reviewers actually look for. The autocomplete uses your full paper as context, so suggestions are relevant to what you're actually writing, not just generic text completion.
What databases does the citation search pull from? Is it just Semantic Scholar or does it
also search PubMed, arXiv, CrossRef?
Bibby AI
@sachin_vishwakarma3 We have a huge list of citation search databases, which combines all of the above mentioned plus Elsevier, Springer, etc. You can also import your citations with Zotero rdf files. What do you generally use?
Co-authoring is often messy — different writing styles, different comfort levels with AI assistance. Can individual authors set their own suggestion preferences within a shared document, or does one setting apply to the whole team?
Bibby AI
@klara_minarikova That is a very interesting suggestion! Right now only one setting applies to the whole team. We can create a separate workflow where multiple suggestions can be merged like Google Docs. Adding this to our Roadmap. Thanks for this feature ask!
Does the AI reviewer go beyond formatting and actually flag gaps in logic or weak arguments like a real conference reviewer would?
Bibby AI
@walsh_fernandes yes the reviewer will flag beyond normal logic, it will behave like a peer reviewer for a conference and take time around 10 minutes to deliver the review.. and you can configure for each conference/journal you plan to submit. It will imitate the knowledge of the reviewers, we specifically trained on the reviews and the knowledge reasoning. It's not perfect though, not comparable to a human yet, but definitely less bias than humans.
When AI suggests references, what’s your approach to ensuring they’re not hallucinated or slightly off?
Bibby AI
@athsara We have strict checks on what qualifies as a proper reference, we have a sub-agent that checks the references it thinks of and we evaluate/weigh the reference based on our benchmarks.