Stars
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
📚 《Deep Agents 实战》—— LangChain 官方大使出品，基于 LangChain / LangGraph 生态，从零构建生产级 AI Agent 的完整指南
A framework for building provenance-based intrusion detection systems with neural networks (KDD'26, USENIX Sec'25)
Algorithm powering the For You feed on X
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
A set of examples based on verl for end-to-end RL training recipes.
[AAAI 2025] Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling
[NeurIPS 2025] One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
Official code repo for NeurIPS 2025 Spotlight paper, "Debate or Vote: Which Yields Better Decisions in Multi-Agent LLMs?"
LLM Council works together to answer your hardest questions
AI agent for autonomous cyber operations
MAD: The first work to explore Multi-Agent Debate with Large Language Models :D
implementation of the paper "APRIL: Towards Scalable and Transferable Autonomous Penetration Testing in Large Action Space via Action Embedding".
💫 Toolkit to help you get started with Spec-Driven Development
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with …
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
OCR-APT: Reconstructing APT Stories through Subgraph Anomaly Detection and LLMs.
MEGR-APT: A Memory-Efficient APT Hunting System Based on Attack Representation Learning