Eric Wu

Paperclip 📎 gives your agent access to millions of full-text biomedical papers. Agents like Claude Code, Cursor, and Codex are powerful research environments, not just for coding. But searching for papers often returns missing or incomplete results because these agents only have access to basic web search. With our release of Sy (sy.gxl.ai), we showed that giving agents access to a deep index of biomedical papers improves literature search (1.6× more accurate, 2.4× faster, and 3.6× cheaper) over Claude Code alone. 🚀 Today, we're releasing Paperclip as a CLI that can be installed directly in your agent IDE! 👉 To install and try it out, go to paperclip.gxl.ai 📖 We also wrote a technical deep-dive into how Paperclip works and why agents take to it really well: gxl.ai/blog/paperclip

@MaziyarPanahi @james_y_zou @_akhaliq @gxl_ai Thanks! Data is updated depending on the data source (e.g., biorxiv is a monthly release). No quotas currently.

@james_y_zou @_akhaliq @gxl_ai This is amazing! I am gonna add this to OpenMed Agent. It has its own PubMed and PMC servers, but this gives more access to more things. How often does it update and are there any restrictions/quotas?

Big Update🤩: #paperclip now includes full papers from all of arXiv, PubMed Central and 150 million abstracts!🖇️ You can give your LLM all that knowledge in one line—all optimally indexed for AI agents. Much more thorough and ~100x faster than web search, and free.

@LH @james_y_zou @gxl_ai Yes! Paperclip creates a Claude Code skill file (if selected) when it is installed. Alternatively, you can use it via MCP. paperclip.gxl.ai/docs

@james_y_zou @gxl_ai How do you plug this into Claude Code? Is there a skill file for it or something?

@Chain_AlphaX @james_y_zou @gxl_ai Not at the tool call level, but overall agent execution. We observe that default Claude Code websearch + webfetch often has to make many sequential calls to answer a question, whereas paperclip grep + map provides very dramatic speedup by performing parallel pre-indexed searches.

@james_y_zou @gxl_ai Wow, 100x faster than Google? Interesting… how?

@girishkaitholil @james_y_zou @gxl_ai *Articles with identical titles are deduped, with preference for PMC over preprints.

@girishkaitholil @james_y_zou @gxl_ai Paperclip doesn't perform deduplication by default, meaning both versions will show in the search results. We found in practice, AI agents are quite good at figuring out which versions are more recent/relevant based on the available metadata (date, journal, etc.).

huge gift to auto research community!

@wenhaocha1 Thanks Wenhao!

@therealRYC @james_y_zou @gxl_ai Hi Robert, Paperclip updates automatically with the latest literature as its made available, depending on the source (e.g., biorxiv makes monthly releases).

@james_y_zou @gxl_ai Cool! How does it update? Does it scrape daily? Or is it manual to update the latest literature?

Very excited for this update!

#paperclip now has a public repo! You can request features and discuss issues here github.com/GXL-ai/papercl…

been using the paperclip.gxl.ai and im just blown away but how much better it makes cc as a research assistant. i feel like they solved something smoothly. an elegant example of 'you need to translate problems to something that a CLI solves'. researchers - out there - try it @james_y_zou

As biology AI models mature, biology-native data infrastructure will be critical in separating the next generation of winning biotechs. It will come down to three things: biology-native data at scale, agentic AI across R&D workflows, and closed-loop lab automation.

@OneManSaas @james_y_zou We don't perform de-duplicating between preprint/published/updated versions, but the agent using Paperclip would have access to metadata like published year, source, etc. so you can instruct your agent to prefer up-to-date papers.

@james_y_zou How does the indexing handle version conflicts when the same paper gets updated or retracted? Been burned by outdated research in production systems before.

You can now give your agent deep knowledge of millions of papers in one line with #paperclip!📎 >8 million papers natively indexed for agents. Much more thorough + often 10x faster than standard deep research. Just add the paperclip mcp (instruction below).

@TimothyKassis @james_y_zou Thanks!

@james_y_zou Nice work!

@_tlynch @james_y_zou Currently Paperclip only includes open-access papers (preprints and published articles)

@james_y_zou does this search both open- and closed-source papers?

@bigpt_dog @james_y_zou Paperclip currently only includes biomedical papers from bioRxiv, medRxiv, and PubMed Central, but we are expanding soon to other sources!

@james_y_zou does it have econ and geopol paper included as well?

A couple of exciting updates from the GXL team today: 1. Sy, our biomedical literature search agent, now has access to 8M+ papers from PubMed Central! Head over to sy.gxl.ai to try it out! 2. We’re releasing Paperclip, a CLI for biomedical papers! Agent IDEs like Claude Code, Cursor, and Codex are more than just for writing code; they are also powerful research environments. But the moment you need to find a paper, you're back in your browser, because the biomedical literature isn't easily accessible to the agent. Paperclip attaches a filesystem of millions of articles directly to your agent, so you can conduct literature search, pull full-text results, and synthesize findings without leaving your IDE. Search results are accessible locally, right alongside your work. We initially built Paperclip as an internal tool to power Sy, our biomedical literature search agent, but found that it works really well with general coding agents, so we’re making it available to other researchers to use. To install Paperclip: paperclip.gxl.ai Learn more: gxl.ai/blog/paperclip