We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference…

PaperBanana: Automating Academic Illustration For AI Scientists

DSPy: The framework for programming—not prompting—language models

Agno turns agents into production software. Build in any framework. Run as a service. Ship to real users.

Idea2Paper Offical Demo

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Extensive tutorials for learning how to build deep learning models for causal inference (HTE) using selection on observables in Tensorflow 2 and Pytorch.

A convenient way to link, deduplicate, aggregate and cluster data(frames) in Python using deep learning

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

Korean-MTEB

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

A library that scrapes Linkedin for user data

<밑바닥부터 배우는 AI 에이전트> 소스 코드 저장소

Code to create the scientists-inventors dataset, as well as the descriptive figures and regressions.

A demo repository showcasing real-time visualization of GraphRAG retrieval processes.

A large-scale open data lake for the science of science research.

21 Lessons, Get Started Building with Generative AI

"RAG-Anything: All-in-One RAG Framework"

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Multilingual Document Layout Parsing in a Single Vision-Language Model

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

A lightweight LMM-based Document Parsing Model

A curated list of resources for Document Understanding (DU) topic