Starred repositories
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.
Texture a whole game level from a gray blockout with image models: plan cameras, paint, project, bake. Real shadows, glTF out.
[Arxiv-2026] Reconstructing Large-Scale 3D Scenes via Overlapping Chunk Alignment and Camera Pose Refinement
Hy-Nomas: Towards Free-form Interactive World Generation
江山时序 · 中国历史交互地图时间轴 (403 BCE – Present) | Interactive Historical Atlas of China across 18 dynasties, 198 territory snapshots, ancient-to-modern place genealogy & classical poetry routes
Matrix-Game 4.0: Streaming Neural Rendering for Playable Games
Reverse engineer anything with agents, from app behavior down to native binaries.
LiteReality-Agent: Turn the real world into simulation-ready environments.
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
S-Space: Exploring Spatial Workspace in Multimodal Models
Harness of Harness: Multi-Day Autonomous Software Development with Continual Improvement
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
🐧 Unified and Stable RSI Platform
The roadmap of long-horizon agents
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering bio…
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
Source-backed feature comparison of memory systems for AI coding agents. No affiliation, no marketing — just facts from public docs.
An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.
3D Reconstruction of Indoor Scenes with a Generative Framework
Open-source 3D architecture software for AECO, scan-to-BIM. Agent-friendly, browser-first, MCP, CLI.
Blockify: Agentic data optimization for enterprise RAG and agentic search. Blockify replaces naive chunking with deduplicated IdeaBlocks — ≈78X accuracy aggregate improvement, 2.29X vector search a…
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
Lore is a next-generation, open source version control system