Stars
a set of SKILLS.md for doing bioinformatics with agents like claude code
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
AI agents running research on single-GPU nanochat training automatically
Research artifacts from Hyra (/ˈhaɪ.rɑː/)
A project implementing various agentic RL based on the Slime post-training framework
Biomni: a general-purpose biomedical AI agent
Harness + per-model results for evaluating the omicos agent on phylobio/BiomniBench-DA. 50 tasks × 7 models, 6-dimension capability radar, cost analysis. omicos runtime source: github.com/omicverse…
The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
FinRL®: Financial Reinforcement Learning. 🔥
One Discrete Word for Visual Reasoning Overtakes Agentic and Latent Methods
Automatically find issues in image datasets and practice data-centric computer vision.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Insightful Tutorials and Papers about Knowledge Graphs
Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.
拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
[ICLR 2026] The official repository for paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval