shushu-internship-tool

把岗位描述变项目，把项目变简历，把简历变面试。

LoongForge

A modular, scalable, and highly efficient training framework for language, multimodal, and embodied models.

future-agi

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

WorldSeed

WorldSeed **Your first AI world.** Give AI a world. Make it yours. **Getting Started**getting-started · **Demo**https://worldseed.morphmind.ai/demo · **Docs**docs/ARCHITECTURE.md **English** · 简体中文docs/README.zh-CN.md --- What is WorldSeed? A world engine where you describe any scenario

OpenMythos

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

HY-World-2.0

HY-World 2.0：A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds EnglishREADME.md | 简体中文README_zh.md "What Is Now Proved Was Once Only Imagined" 🎥 视频 https://github.com/user-attachments/assets/b56f4750-25c9-48fb-83ff-d58526711463

personalized-podcast

Turn any content into a personalized AI podcast. NotebookLM-style, except you control the script, voices, and hosts. Listen in Apple Podcasts, Spotify, or any podcast app.

mathcode

MathCode MathCode: A Frontier Mathematical Coding Agent ``` ███╗ ███╗ █████╗ ████████╗██╗ ██╗ ██████╗ ██████╗ ██████╗ ███████╗ ████╗ ████║██╔══██╗╚══██╔══╝██║ ██║██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██╔████╔██║███████║ ██║ ███████║██║ ██║ ██║██║ ██║█████╗ ██║╚██╔╝██║██╔══██║ ██║ ██

mini-coding-agent

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

mempalace

The highest-scoring AI memory system ever benchmarked. And it's free.

autoclip

AutoClip : AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具

OpenAnt

OpenAnt from Knostic is an open source LLM-based vulnerability discovery product that helps defenders proactively find verified security flaws while minimizing both false positives and false negatives. Stage 1 detects. Stage 2 attacks. What survives is real.