Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Talk to research papers like talking to authors - Python package with AI agent for arXiv papers
| Date | Stars |
|---|---|
| 2026-07-31 | 762 |
| 2026-08-06 | 767 |
Today
+5 stars today
This week
— stars this week
This month
— stars this month
Momentum
5.0
growth rate 0.00%/day
# deepxiv-sdk **DeepXiv is an agent-first paper search and progressive reading tool.** Install it with `pip`, start using it immediately, and let the CLI auto-register an API token on first use — no setup needed before your first query. > ### 🚦 Service status — [live status page](https://data.rag.ac.cn/status) > > - 🟢 **arXiv retrieval & reading** — online. We aim for a T+1 sync with arXiv (subject to arXiv's own ~1-day API latency). > - 🔴 **bioRxiv / medRxiv** — **temporarily down due to a server-side issue. We're working to restore it as soon as possible.** Related commands return `503` in the meantime. > - 🔑 Lost your token? Recover it at [data.rag.ac.cn/token-lookup](https://data.rag.ac.cn/token-lookup) (Google sign-in supported). > - ℹ️ Data processing is currently trying a broader mix of models. If a TLDR looks off (e.g. truncated thinking content), please open an issue — we'll fix it. - **🚦 Live Status**: [https://data.rag.ac.cn/status](https://data.rag.ac.cn/status) - **📚 API Documentation**: [https://data.rag.ac.cn/api/docs](https://data.rag.ac.cn/api/docs) - **📄 Technical Report**: [](https://arxiv.org/abs/2603.00084) - **📖 中文文档**: [README.zh.md](README.zh.md) <p align="center"> <img src="./assets/demo.gif" width="60%"> </p> > 🚀 **Live Demo**: built on the deepxiv CLI in ~1 hour with vibe coding — try the [DeepResearch demo](https://demo.rag.ac.cn/). A full-stack research platform is on the way. --- ## What DeepXiv Does DeepXiv is built around two workflows that matter for agents: 1. **Search + progressive content access** — read papers in layers, not all at once. 2. **Trending + popularity signals** — find what's worth reading right now. The core idea: an agent should **search first, judge quickly, then read only the most valuable parts** — instead of blindly loading full papers. ## Quick Start ```bash pip install deepxiv-sdk ``` On first use, deepxiv auto-registers a free anonymous token (1,000 requests/day) and saves it to `~/.env`: ```bash deepxiv search "agentic memory" --limit 5 ``` For the full stack (MCP server + built-in research agent): ```bash pip install "deepxiv-sdk[all]" ``` ## Progressive Reading: search → judge → read The CLI is the primary interface. A few flags drive layered reading so agents don't load full papers unless they truly need to: ```bash deepxiv search "agentic memory" --limit 5 # 1. find candidates deepxiv paper 2409.05591 --brief # 2. decide if it's worth reading deepxiv paper 2409.05591 --head # 3. inspect structure & token distribution deepxiv paper 2409.05591 --section Method # 4. read only the valuable parts ``` - `--brief` — title, TLDR, keywords, citations, GitHub URL - `--head` — sections overview and token distribution - `--section NAME` — read a single section (e.g. `Introduction`, `Method`, `Experiments`) - `--preview` / `--raw` / *(no flag)* — ~10k-char preview / full markdown / full paper --- ## CLI Reference ### Search papers Basic search (arXiv by default): ```bash deepxiv search "transformer" --limit 10 deepxiv search "agentic memory" --limit 20 --format json ``` **Filter by author, org, and category** (comma-separated): ```bash deepxiv search "image generation" \ --authors "Shitao Xiao,Zheng Liu" \ --orgs "Beijing Academy of Artificial Intelligence" \ --categories cs.CV \ --limit 5 ``` > `--authors` and `--orgs` are filters *and* ranking signals; `--categories` is a pure filter. **Filter by venue** (`--venue` is repeatable; common aliases match automatically): ```bash deepxiv search "diffusion model" --venue NeurIPS --limit 5 deepxiv search "language model" --venue NeurIPS --venue ICLR --limit 5 # Add a conference year (when the venue's year is indexed for those papers): deepxiv search "diffusion model" --venue NeurIPS --venue-year 2025 --limit 5 ``` > `--venue NeurIPS` also matches `NIPS` / `Neural Information Processing S
Excerpt of 20,193 characters
Read on GitHub
Tommy Chien · BAAI · China
45
zhengliu · Microsoft · China
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:971b57070b983a4c, desc:ai agent