Starred repositories
slime is an LLM post-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.
Stateful agents that are like people, with memory, identity, and the ability to learn and adapt
SWE-Marathon: 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
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/
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.