I mapped 8.5M research papers into an interactive atlas
When I read papers, I have to jump between multiple tabs to find the dataset, code, videos, peer reviews, and so on. I tried to fix this with this project.It started as a project just for papers on arXiv, but after its initial success on Twitter (got like 1.9k views: the most I have gotten for a post), I have now expanded it to include other openly available papers from PubMed Central, bioRxiv, medRxiv, and eLife. These papers have been linked with their genes, proteins, diseases, drugs, clinical trials, 3D protein structures, code, and cited and similar papers.This project now has four parts:First, a map. I embedded nearly 8.5M papers (with SPECTER2), ran UMAP for 2D representation, and rendered them as a scatterplot. The dots can be clicked to see brief information about the papers, like an LLM TLDR, key findings, peer reviews, linked entities, and more. The clusters are also labeled, though you might have to zoom in.Second, I built a detailed paper page for each paper. They give you the paper's full text, images, videos, peer reviews (from OpenReview), GitHub links, Hugging Face dataset/model links, clinical trials, genes, diseases, 3D protein structures, cited papers, and similar papers. You can also copy the whole page, including the full paper text and image URLs, as markdown for your LLM.Third, I have released an extension so you can read all this information in your sidebar by clicking "open in Tomesphere" that shows up in arXiv, PMC, bioRxiv, Google Scholar, or medRxiv. I have tried to provide as much information as possible in the extension, though for things like viewing all the images or a 3D protein structure, you might still have to go to the paper page using the link provided in the extension.Fourth, all this data is available for your LLM via MCP. The MCP does have a 50-query free limit (this jumps 10x with signup).Note: this project is still in beta, so papers might have some mismatched information. I am rolling out feedback form
FL score
out of 100
Verdict
high confidence
Competition
No competitor data yet
Trend
No signal yet
A searchable atlas of 8.5M research papers with embedded metadata, peer reviews, and code links that reduces tab-switching for researchers.
The pain
The gap
Build angle
Strengths
- Solved a real workflow problem with working prototype and measurable traction (1.9k views, extension deployed)
- Multi-format access (map, paper pages, browser extension, MCP) reduces friction for different user behaviors
- 8.5M papers is substantial scale; SPECTER2 + UMAP clustering is technically sound
- Integrated data (genes, proteins, diseases, clinical trials) adds value beyond existing tools
- Early signal on Twitter suggests product-market fit potential in research community
Risks
- Data quality issues acknowledged (mismatched information in beta). This erodes trust quickly with researchers who rely on accuracy.
- No clear monetization path. Free tier with MCP limits won't sustain infrastructure costs at 8.5M papers. Researchers resist paying for tools.
- Dependency on third-party data (OpenReview, GitHub, Hugging Face, clinical trial APIs). If these change or restrict access, the product breaks.
- Competitive threat from Google Scholar, Semantic Scholar, and LLM-native research tools. Unclear what defensible moat exists.
- Usage metrics missing. 1.9k Twitter views ≠ active users. No data on extension installs, repeat usage, or LLM query volume.
- Maintenance burden. Keeping 8.5M embeddings fresh and linked data current requires ongoing engineering. Unclear if solo builder can sustain this.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Five lenses, one composite. How scoring works
The angle
No market research recorded for this idea yet.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “I mapped 8.5M research papers into an interactive atlas”.