The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).
Repository Index
132,241 visible repositories in the index
481–504 of 771 · Most stars
开源的每日 arXiv / OpenReview 论文推荐与 AI 阅读平台,支持 GitHub Actions 自动更新、GitHub Pages 部署与论文问答。
- arxiv
- arxiv-papers
- openreview
- paper-recommendation
An Automatic Prompt Optimization Framework for Large Language Models
An Open-Source AI Writing Project.
- agentic-workflow
- ai-agents
- ai-writing
- creative-writing-ai
An algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video.
ICCV 2023-2025 Papers: Discover cutting-edge research from ICCV 2023-25, the leading computer vision conference. Stay updated on the latest in computer vision and deep learning, with code included. ⭐ support visual intelligence development!
- iccv
- iccv2023
- 3d-graphics
- 3d-reconstruction
The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.
- audio-ai
- audio-generation
- audio-llm
- music-generation
AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.
[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
- 3d
- 3d-generation
- 3d-scene
- 3d-scene-generation
FAME Automates Malware Evaluation
- malware
- malware-analysis
- malware-research
- framework
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
- ai-for-science
- agentic-ai
- ai4science
《Claude for Legal — 中国法版本》本仓库是基于 Anthropic 开源项目 `claude-for-legal` 改造的中国法适配版本,面向中国法律实务场景,提供可在 Claude Code、codex 和deepseek harness中运行的法律 Agent、技能和 MCP 数据连接器参考框架。
- ai-governance
- china-law
- chinese-law
- claude
Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024)
Pure-Python protocol tools and research notes for X.com, with VibeLoft Twitter account datasets
Bayesian active learning library for research and industrial usecases.
- active-learning
- deep-learning
- machine-learning
- pytorch
Real-time multi-person action recognition from OpenPose skeleton sequences, with tracking, feature extraction, model training, and inference pipelines for research and prototyping.
- action-recognition
- openpose
- machine-learning
- time-series
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
- research
- multi-agent-reinforcement-learning
- multi-agent-systems
- multiagent
Research code accompanying AlphaGenome
Extract and aggregate threat intelligence.
- ioc
- indicators-of-compromise
- threatintel
- threat-intelligence
Deep research agent to help you find the best GitHub repositories 🕵️!
TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.
- 3d-reconstruction
- cvpr2024
- gaussian-splatting
- generative-3d
AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude Code, Codex, Cursor.
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
- accuracy-decline
- ai-safety
- audit-trail
- fact-checking