AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent agents in simulated environments.
- agentsociety2
- ai-social-scientist
- agent
- multi-agents
A curated list of Multimodal Related Research.
- awesome
- multimodal-research
- multimodal-learning
- multimodal
中文版的ai地牢,直接使用的openai的ChatGPT api作为讲故事的模型。
A research toolkit for particle swarm optimization in Python
- particle-swarm-optimization
- optimization-tools
- pso
- global-optimization
Security Research from the Microsoft Security Response Center (MSRC)
Interactive Python & C++ apps for desktop, mobile, and web - powered by Dear ImGui. Stop fighting GUI frameworks. Start building.
Big & Small LLMs working together
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
- agentic-rl
- expert-parallelism
- fsdp
- llm
[IEEE T-PAMI 2023] Awesome BEV perception research and cookbook for all level audience in autonomous diriving
- autonomous-driving
- birds-eye-view
- camera-detection
- lidar-detection
DRAKVUF Sandbox - automated hypervisor-level malware analysis system
把英文论文读成舒服的中文:本地 PDF 论文翻译、原文对照、边读边问 AI、文献管理。Read English papers in comfortable Chinese.
PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend
Agent skills for daily paper discovery, critical reviews, and connected research notes. Supports English and Chinese.
Minimal and annotated implementations of key ideas from modern deep learning research.
This is a dataset for fake news detection research
Uncommon Objects in 3D dataset
Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
YACS -- Yet Another Configuration System
PoC for Zerologon - all research credits go to Tom Tervoort of Secura
A reconnaissance framework for researching and investigating Telegram.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
A simulation platform for versatile Embodied AI research and developments.
Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text.