Stars
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
This is a FastAPI application that uses a LangGraph workflow to route parking-related questions to specialized agents.
麦麦专属点单管家 —— 由个性化规则驱动的麦当劳点单 Skill。规则从对话里自动抽取，冲突按七层优先级仲裁并讲清为什么。基于麦当劳中国官方 MCP。
COOKer可以稳稳接住私人饮食管家这个身份，他会记住你相对应的饮食习惯、教你做菜从头到尾，当然也有属于你的外卖休闲时刻
An Adversarial Co-Evolution Framework for LLM Agent Safety
Turn PDFs, books and papers into interactive learning webpages｜将复杂材料转化为可追溯、可测验、可做笔记的学习网页
A lightweight microVM sandbox runtime for agents, automation, and untrusted workloads.
🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
Open-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins.…
Your Best City Test（你的本命城市测试）是一款基于微信小程序的趣味性格测试应用。通过 100 道生活方式选择题，从气候偏好、饮食口味、生活节奏、文化氛围、消费水平等 12 个维度勾勒用户画像，并与 49 座中国城市逐一计算契合度，帮你找到最匹配的「本命城市」。小程序支持中英文双语切换，结果页提供雷达图可视化、12 维度约 200 字的详细匹配报告，还为每座推荐城市附上 5 …
麦门权益管家 / McPerks Planner - 基于麦当劳官方 MCP 的权益管理 Skill（非官方参赛作品）
Decision-first dashboard compiler and governance layer: decide whether a dashboard should exist, enforce evidence-backed semantics, and verify the delivered artifact.
See what your coding agent (Claude Code, Codex, Kimi) sends to the model — local proxy + web dashboard
BKN Foundry is the Ontology back-end foundation of OpenBKN. It transforms ontology-driven business semantics into runtime services: data, logic, actions, security governance, and observability.
An open source book reader for kids, built for my daughter
Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
Edit Banana: A framework for converting statistical formats into editable.
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving
Estimating dense correspondence from region correspondence.
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
TI mmWave Radar IWR1843/AWR2243+DCA1000EVM Raw ADC IQ data and UART data capturing