- Beijing
- All languages
- C
- C#
- C++
- CMake
- CSS
- Cuda
- Cython
- Dart
- Gnuplot
- Go
- HCL
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Lex
- Lua
- MATLAB
- MDX
- MLIR
- Macaulay2
- Makefile
- Markdown
- Mojo
- Nim
- OpenEdge ABL
- PHP
- PLSQL
- PostScript
- Praat
- PureBasic
- Python
- R
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Swift
- TeX
- TypeScript
- Typst
- Verilog
- Vue
Starred repositories
An open-source tool for LLM prompt optimization.
Embedding Projector是Google开源的高维数据可视化工具,本项目基于这款交互式可视化Web应用程序搭建一个可以进行高维数据分析的系统。
Towards a More Autonomous Agent System
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
An engineering philosophy that treats the agent as a worker: the system prompt is a JD, skills are certifications, model tiers are degrees, memory is a career record, the sandbox is a work computer…
A collection of agent trajectory analysis techniques and benchmark
基于 OpenSandbox 的 AI Agent 轨迹数据合成工作台
A practical guide to building enterprise AI agents across their full lifecycle.
AgentInsight 是面向 AI Agent 应用的观测与分析平台,帮助团队更清晰地追踪 Agent 的运行过程、调用链路、输入输出、异常与效果表现。 AgentInsight is an observability and analytics platform for AI Agent applications. It helps teams trace agent executio…
An autonomous agent that profiles, optimizes, and validates AI training code.
RSIGym: A Flexible Environment for Recursive Self-Improvement
Optimize prompts, code, and more with AI-powered Reflective Optimization
The absolute trainer to light up AI agents.
A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Rubrics
The offical repo for "Dream-RSI: Recursive Self-Improvement through Evolving Worlds"
Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.
Deep Research as Rubric for Reinforcement Learning
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
微信读书全本导出工具 — Playwright + Canvas Hook 提取完整书籍内容为 Markdown
本项目是《AI Agents in Action》第二版的中文译本,是一本智能体系统构建与应用的实战指南——目标不止于打造自主实体,更在于开发能够切实应对并解决现实问题的智能体。 全书从大语言模型(LLM)的基础应用出发,逐步深入到智能助手、多智能体系统与自主智能体的构建,系统讲解智能体系统的关键组成部分:角色、工具与行动、知识与记忆、检索与增强、推理与规划、评估与反馈。第二版将五个功能层作…