Starred repositories
Open-source AI skills and plugins for EB-1 and EB-2 NIW immigration petitions — from evidence organization to RFE response.
Claude code environment for laywers
slime is an LLM training framework for RL Scaling.
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
Write HTML. Render video. Built for agents.
Personal-Model First Self Evolving AI Agent 🐘
The paper list of "Memory in the Age of AI Agents: A Survey"
My solo-built Linux systems archive — original notes, kernel experiments & 100+ self-authored blog posts. 🐧→🤖
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Petition letter latex template for EB1 and EB2-NIW
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Agents that self-improve with experience
[NeurIPS 2026] An ultra long-horizon SWE benchmark
IronClaw is an Agent OS focused on privacy, security and extensibility
Figure skating practice tracker with Tauri + React
Yuan - Personal Investment Operating System
TradingAgents: Multi-Agents LLM Financial Trading Framework
🙌 OpenHands: AI-Driven Development
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Solutions for Object Oriented Design Problems
This is the notes of the way of machine learning study. You may find something useful in it.
推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/