Skip to content
View Yimi81's full-sized avatar

Block or report Yimi81

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Python 1,336 144 Updated Nov 16, 2026

94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.

TypeScript 3,958 353 Updated Nov 6, 2026

Texture a whole game level from a gray blockout with image models: plan cameras, paint, project, bake. Real shadows, glTF out.

TypeScript 219 18 Updated Nov 13, 2026

[Arxiv-2026] Reconstructing Large-Scale 3D Scenes via Overlapping Chunk Alignment and Camera Pose Refinement

Python 406 11 Updated Nov 5, 2026

Hy-Nomas: Towards Free-form Interactive World Generation

Python 584 53 Updated Nov 12, 2026
Python 332 17 Updated Oct 20, 2026

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

JavaScript 6,817 799 Updated Nov 16, 2026

An Open Index of RSI Papers

JavaScript 611 37 Updated Nov 16, 2026

Matrix-Game 4.0: Streaming Neural Rendering for Playable Games

Python 2,930 305 Updated Oct 29, 2026

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript 464,237 113,614 Updated Nov 17, 2026

LiteReality-Agent: Turn the real world into simulation-ready environments.

Python 667 63 Updated Oct 3, 2026

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Python 2,866 250 Updated Aug 12, 2026

S-Space: Exploring Spatial Workspace in Multimodal Models

Python 185 5 Updated Oct 13, 2026

Harness of Harness: Multi-Day Autonomous Software Development with Continual Improvement

TypeScript 197 22 Updated Oct 20, 2026

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

JavaScript 97,178 6,634 Updated Nov 17, 2026

🐧 Unified and Stable RSI Platform

TypeScript 3,254 353 Updated Nov 16, 2026

Code for the ShapeR research paper

Python 903 66 Updated Apr 30, 2026

The roadmap of long-horizon agents

873 57 Updated Nov 2, 2026

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…

Python 57,469 5,051 Updated Nov 16, 2026

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.

TypeScript 126,811 8,046 Updated Nov 17, 2026

Source-backed feature comparison of memory systems for AI coding agents. No affiliation, no marketing — just facts from public docs.

HTML 177 25 Updated Nov 16, 2026

An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

TypeScript 1,855 180 Updated Aug 28, 2026

3D Reconstruction of Indoor Scenes with a Generative Framework

Python 640 50 Updated Feb 9, 2026

find 3d boundboxes in your splat

HTML 109 26 Updated Jul 20, 2026

Open-source 3D architecture software for AECO, scan-to-BIM. Agent-friendly, browser-first, MCP, CLI.

TypeScript 25,562 3,178 Updated Nov 16, 2026

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…

Python 316 39 Updated Apr 22, 2026

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!

Python 10,860 1,013 Updated Nov 16, 2026

A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.

Python 2,985 218 Updated Nov 13, 2026

Lore is a next-generation, open source version control system

Rust 9,162 489 Updated Nov 16, 2026
Next