realDevo
Follow
Stars
[NeurIPS 2025] Codes for paper Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge
efflux-desktop-ui
G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
CXLMemSim: A pure software simulated CXL.mem for performance characterization
Code for "Filling MIDI Velocity using U-Net Image Colorizer" (CMMR2025) PyTorch implementation for filling MIDI velocities from given MIDI notes.
A cloud drive app using Cloudflare R2 storage
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
A neural network for emotion recognition based on multimodal physiological signal
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
A cross-platform instant messaging client application built with Tauri and Vue 3, featuring one-to-one chat, group chat, file transfer, audio/video calling, screen recording, screenshot capture, an…
https://dev.to/answeryt/the-demo-spell-and-production-dilemma-of-ai-agents-how-i-built-a-self-learning-agent-system-4okk
Automatically extracts long texts into structured dialogue datasets via LLMs, with built-in validation, pairing, ChatML export, CLI/FastAPI/GUI support, concurrency, and checkpoint resume. 通过LLM自动将…
Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model
PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.
A comprehensive, production-ready framework for building intelligent AI agents with advanced capabilities including tool calling, persistent memory, intelligent concurrency, and event-driven observ…
开箱即用。基于 AI 完整保留排版的 PDF、 PPTX 、 DOCX 、 EXCEL 、 TXT 、 HTML文档全文双语翻译
🔥 AngusInfra is a foundational framework for rapidly developing multi-tenant web applications, built on the Enterprise-level development framework SpringBoot.
A lightweight and modular image processing pipeline written in Go. Includes utilities for cropping, resizing, watermarking, format conversion, and more.
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Nexent is a zero-code platform for auto-generating agents — no orchestration, no complex drag-and-drop required. Nexent also offers powerful capabilities for agent running control, data processing …
A small system developed by C and QT in college classes
AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai
Bingo is a desktop application designed specifically for ad developers. It helps you quickly build, test, and publish cross-platform playable ads. Whether you're targeting Facebook, Unity, AppLovin…
Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling