Image agents

Not a framework. A file format for agent-to-agent handoffs — provenance, parallel safety, and human visibility by design. Model-agnostic. Framework-agnostic. Open spec, MPL-2.0.

Model Shell Protocol: an application-owned command runtime that gives AI agents OS-like workspace semantics.

AI for hardware design workflow

A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flash. Ships the residency calculator, measurement harnesses, and the build recipes behind it. Predictions validated against public benchmarks.

结合实时天气与出行场景的 AI 穿搭助手，支持穿搭照片识别、个人穿搭库管理与每日搭配建议。

Timeless principles and best practices for working with language models - tooling-agnostic, future-proof, and clear.

Convert images into captivating audio stories using image-to-text, language models, and text-to-speech technologies. Upload images, generate stories, and listen to the narrated audio clips. A fun project combining AI and creativity.

🔍 AI search engine with self hosted LLMs via Ollama

The Bencao RAG Medical Intelligent Assistant is a powerful AI-based medical knowledge question-answering system, designed to enhance user experience in knowledge-intensive tasks by integrating context awareness, internet access, knowledge graphs, and retrieval-augmented generation.

Surrogate OS, The professional identity engine that synthesizes complete AI experts from a role input — and deploys them across chat, voice, avatar, and humanoid interfaces.

About A visual interface for creating and customizing LLM agents using drag-and-drop components. Designed for both developers and non-developers.

Persistent visual memory for AI agents — capture screenshots, embed with CLIP ViT-B/32, compare, recall. MCP server + Rust core library.

Midjourney — full premium build for Windows with pro features unlocked. Creative Suite Pro Pack

streamlit region:us

gradio image-to-image artifact-removal flux region:us

Sell anything with a single photo. An autonomous creator monetization agent that turns an image into a live, zero-fee Stripe checkout page in seconds.

The ledger layer the stablecoin payment stack was missing. Double-entry, event-sourced, agentic-first. Fiat + on-chain. Built for cross-border.

Local AI platform: run LLMs, Stable Diffusion, Whisper, TTS, video & 3D generation offline — open-source Ollama + ComfyUI alternative in one binary.

AI-to-UI IR Protocol Layer — The Last Mile from AI to Human. Includes Lucid UI Skill for professional AI-generated interfaces.

AI Tools Knowledgebase

An agentic adaptive RAG system designed for intelligent query routing and multi-agent collaboration.

Simple Generative AI enabled Streamlit web application that converts speech to-image.

Open source & private LLM apps on your desktop

A meticulously curated collection of hands-on Jupyter notebooks, designed to illuminate the comprehensive application of MLflow across a spectrum ranging from foundational Machine Learning principles to pioneering Generative AI paradigms.

LangChain Text Summarization and Image Generation

Notebooks demonstrating vector search & RAG design patterns with Redis Python clients.

A dynamic, industry-agnostic AI agent framework designed for seamless integration across multiple AI providers and models.

SUBSUMPTION PATTERN LEARNING (SPL) MULTI-AGENT FRAMEWORK: Hierarchical foundation model agent architecture that reduces costs by 10-50x through intelligent suppression of expensive foundation model calls. Grounded in R. Arkin's behavior-based robotics and R. Brooks' subsumption architecture, SPL brings 40+ years of proven autonomous systems design

Vendor-agnostic AI agent configs with production-minded architecture. Compose once, deploy in one command, and keep all tools aligned to one maintainable source of truth.

This project is a multi-agent customer service chatbot designed for an e-commerce platform. The chatbot employ specialized agents handle distinct tasks to ensure efficient and accurate interactions. The chatbot aims to enhance user experience by streamlining order processing, answering FAQs, and providing personalized recommendations.

This is a Rasa NLU based chatbot created by Utor AI that functions as a personal assistant to the students of Vardhaman College of Engineering.

The FirstAid App is an AI Android application designed to provide quick and accessible first aid information for emergencies. It offers users step-by-step guidance to handle common medical situations effectively.

In this model I have created a basic AI chatbot Interface with External plugin abilities; with visual basic An Interface AI_Contracts enables for Intefacing with the AI; Implementing the Interface and placing in the the compiled DLL into the APP\Plugins folder enables for the AI_Interface to discover and call the plugin obtaining a response to be returned to the user; The project was design in 4 stages ; Each stage or milestone enables for the development and extension of the Chatbot to become a enriched product worthy of public release;

A Line bot. Was meant to be twin bot but the user account bot doesn't work anymore (because it used carpedm20's unofficial client).

Chain of Images for Intuitively Reasoning

A beautiful design, customizable AI chatbot built with Next.js.

Cross-platform mobile application with multiple features targeting agricultural community

This project implements a simple AI chatbot that interacts with Twitch chat, using a Live2D avatar to animate and speak in response to user input.

🍳 Find recipes from just a photo of the ingredients with AI.

TerraMours前端，基于vue3.0+ts+naive UI+vite的后台管理系统。实现用户管理、角色管理、菜单管理等功能。

A versatile JavaScript library for designing and managing intelligent agents capable of interacting with AI-driven chat models, leveraging OpenAI's GPT for dynamic conversations and task automation.",

RL vs. 1/n and Mean-Variance in the Portfolio Allocation Problem. A Bachelor's thesis at Utrecht University.

Nodejs library for interacting with Open AI's Dalle-2 AI

🐳 Docker Images for chatgpt-retrieval-plugin 🤖

Generate a WhatsApp-style HTML page from an exported chat, with support for images, videos, audio, PDFs, and optional audio transcription.

A Home Assistant custom integration that facilitates AI tasks using Azure AI

The Multi-Agent RLRM (Reinforcement Learning with Reward Machines) Framework is a library designed to facilitate the formulation of multi-agent problems and solve them through reinforcement learning. The framework supports the integration of Reward Machines (RMs), providing a modular and flexible structure for defining complex tasks.

React Native port of AI Image Generator, Powered by OpenAI & Azure

Bring ChatGPT & Dall-E into your CLI as a specialized personal assistant.

A dynamic learning assistant designed to simplify the onboarding and training process for new hires. Users can upload documents or enter URLs for training materials. Built with Spring Boot, @Langchain4j and spring-ai

RoBC is an online learning LLM router designed for dynamic production environments. Using Thompson Sampling and semantic clustering, it continuously adapts to changing model quality—no retraining required.

SOPHIA III is a dynamic AI agent designed to provide intelligent automation and task management across various AI providers. With her advanced capabilities, Sophia III orchestrates instructions and executes complex tasks with remarkable efficiency.

This repository provides a PyTorch implementation of a video diffusion model, similar to OpenAI's Sora, allowing you to train and generate videos from text prompts using a configurable architecture and diffusion process.

A production-grade, AI-powered system designed to transform digital chaos into structured intelligence.

A production-grade AI chat platform supporting 5 LLMs (Gemini, GPT-4, Mistral, Cohere, DeepSeek) with RAG-powered document intelligence, real-time web search via Tavily, image understanding, live streaming responses via Socket.io, and Redis-backed secure authentication.

LLM Engineer's Handbook by Paul Iusztin and Maxime Labonne with pixi.

MCP server for Bloomfilter, a domain registration service for AI Agents.

Steuermann is designed as a domain-agnostic, on-premise AI runtime. It can be extended with profiles to adapt to specific use cases.

This repository is continuously updated with new architectures and improvements to stay at the forefront of AI agent design.

A 7-agent pre-release audit pipeline for software products. Generic, reusable, AI-native. Inspired by Garry Tan's gstack.

🦞 Agent-native messaging — where AI agents and humans are equal participants. Open source, self-hostable, MCP-ready.

MindForge is a Python library designed to provide sophisticated memory management capabilities for AI agents and models. It combines vector-based similarity search, concept graphs, and multi-level memory structures (short-term, long-term, user-specific, session-specific, and agent-specific) to enable more context-aware and adaptive AI responses.

⚕️ Multi-agent SLM system for medical question answering — domain-aware, private-by-design, cloud-free

🖥️ Mistral_Desktop is a desktop application designed to provide an optimized Mistral experience.

⚡ Pen2PDF Suite – an all-in-one 🚀 productivity platform ✨ with 🤖 AI-powered text extraction (PDF/Images → Markdown 📝), 📅 smart timetable management (CSV/Excel import 📊), ✅ todo lists with subtasks📈, 🧠 AI-generated notes library 📚 and 💬 Isabella AI assistant (OpenAI/Microsoft/llama/Mistral/LongCat/Gemini models 🔄)for context-aware help 🧩.

AI-Driven CAD modeling agent - Transform design concepts into precise 3D CAD models

An open-source, serverless reference implementation for agentic commerce: pay-per-use generative AI, physical goods, and digital goods, where embedded wallets and autonomous AI agents settle USDC stablecoin micropayments over the x402 protocol using Amazon Bedrock AgentCore payments on AWS

A programming language designed for AI agents. No parser, no syntax — agents produce AST directly as JSON. Statically typed, effect-tracked, contract-verified, compiled to WASM via MCP.

一个 简单的 AI 投资助理，管理股票（美股、港股）和基金（国内基金），同时具备类似 Hermes 自迭代学习的能力

Self-hostable digital restaurant menu — Next.js + Cloudflare Workers + D1, with an optional OpenAI-powered chat assistant. One menu, one deploy. PolyForm Noncommercial.

MCP server for Cisco Packet Tracer 9 — let Claude/ChatGPT design, build and validate Cisco network topologies in real time (OSPF, BGP, VLAN, NAT, VoIP, QoS, IPv6, wireless). 57 MCP tools, live HTTP bridge, TypeScript on Bun.

Explore state-of-the-art Text-to-Image AI models with our Image Generation project. Our Streamlit app leverages models like SDXL, BREA v2, DreamShaper v7, DALL-E 2, and Anime Diffusion to generate stunning images from textual prompts. Experience AI creativity at its finest!

NSFW AI Roleplayer bot with image generation.

AgentAz™ — an open, design-time governance specification for AI agents, with 60 reference blueprints. Documents each agent's Trust Level, worst-case action, and boundaries.

A wallet for your agents to onboard and pay. Agentic MPP / x402 payments from your machine - CLI + MCP server.

Opinionated design language + token-driven React components. 31 presets, 70+ components, one markdown file. Built to kill the AI-generated aesthetic.

DSN-exp: The next-generation Agent Infrastructure Cybernetics Framework (AICF). Gateway controls, model deployment, app/harness designing and runtime infrastructure management included.

Open-source Android computer-use agent with a self-hostable backend

A simple mobile interface for generating images from text prompts via OpenAI. Quick setup, minimal UI, instant outputs.

Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hybrid retrieval over a typed, governed corpus, sub-second at 50k notes; your files stay plain markdown.

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

Vision-primitives MCP server for text-only LLMs: describe, locate (coordinates), OCR with bbox, annotate, crop, zoom, automated anomaly scanning, computer use — powered by Xiaomi MiMo V2.5. Single-file Python, Pillow-only dependency.

Open-source hardware engineering skill library for AI agents, covering PCB, embedded hardware, power, EMC, validation, and board-level design.

Agent-native, self-verifying raster→SVG vectorizer + SVG→PNG (CLI + skill). Wraps VTracer/Potrace; auto-routes by image type, curve-smooths to editable SVG, self-verifies via re-rasterization. Agent-customizable flags (--detail, --solid-background, …) turn a user's plain request into the result.

🗒️ A self-hosted personal fitness coach on Telegram, powered by the Claude Agent SDK with a Notion knowledge base and Google Calendar for scheduling. Logs workouts, plans your week, reads meal photos and voice notes, and sends reminders.

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover/search/quota) for DeepSeek Harness (DSH)

WorkForge is a Windows MCP gateway that lets ChatGPT inspect files, resume Git work, make SHA-guarded edits, read images, and run supervised PowerShell jobs.

Create AI marketing videos and images from inside Cursor. Human-approved Meta ad workspace with Arcads creative generation.

58 world-class design systems (Linear, Stripe, Apple, Vercel, Spotify, Ferrari + 52 more) packaged as a single Paperclip AI agent skill. Based on VoltAgent/awesome-design-md.

Photon-hosted iMessage transport and settings UI for DeepSeek Harness

800+ real-world ML & LLM system design case studies from 150+ companies Google, Meta, Netflix, Uber, Airbnb & more. Production AI, not theory.

Open-source, local Windows AI website builder & web-design studio — AI builds the site, you refine it by hand on the live render, every edit verified. BYOK / your own AI subscriptions. MIT.

Curated prompts, official samples, templates, and model notes for ChatGPT Images 2.5 / GPT-Image-2.5 Flare & Sunburst

Infinite whiteboard spatial clustering engine & theme aggregator (Miro Assist)

AI assistant that aids in workflows and design, dedicated to creating excellent AI assistants and automated workflows. It is ready to use out of the box, with specific application scenarios and parameters already optimized. As it continues to upgrade, it will usher in a more intelligent future!

智元 IIM 是一款开源的网页版即时聊天系统, 同时拥有AI聊天对话功能, 支持ChatGPT、Midjourney、文心一言、讯飞星火、通义千问等AI助手功能

This project provides evidence for AI-Assisted Video Forensics

A TypeScript MCP Server that converts ComfyUI workflows into parameter-configurable tools for AI agents. | 将 ComfyUI 工作流转化为参数可配置的 MCP 工具，供 AI 代理通过自然语言驱动图像与视频生成。

A CLI tool for AI Agents to handle file operations and cloud storage with JSON output. Support for S3, R2, MinIO, and more. Token-aware, secure, and agent-first design.

Plain Java Agent with Claude LLM