- Hangzhou, China
- https://walktree.github.io
Lists (3)
Sort Name ascending (A-Z)
Stars
StreamingVLM: Real-Time Understanding for Infinite Video Streams
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Be…
Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks
WeChat local data CLI with daemon architecture
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sa…
🔥 Official impl. of "DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing".
The absolute trainer to light up AI agents.
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
An agentic skills framework & software development methodology that works.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
The agent that grows with you
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Lightweight, open-source AI agent for your tools, chats, and workflows.
一个将 Dify 应用程序转换为 OpenAI API 接口的网关服务,使您可以使用 OpenAI API 兼容的方式访问 Dify 的 LLM、知识库、工具和工作流程。
A Dify tool plugin for encoding and decoding Base64 text and image files.
Tutorials, Guides and Agent Skills Directories
A smart, powerful, and beautiful excalidraw drawing tool.Draw Professional Charts with Natural Language
MotionStream: Real-Time Video Generation with Interactive Motion Controls
微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。
这是一个基于人工智能的网页应用程序,用于为小红书生成和自动发布内容。它通过模型上下文协议(MCP)集成了多种工具和服务,实现了从主题输入到内容发布的全自动化流程。
A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…
Nano Banana(nanobanana),GPT-5(GPT5),GPT-4o(GPT4o) Image Prompts,Nanobanana Prompts,nanobanana提示词
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。