Image agents

This repository is a hub for AI Agent projects, including GitHub Sentinel, LanguageMentor, and ChatPPT, designed to enhance enterprise workflows, language learning, and multimodal interaction. Explore a growing family of agents geared towards revolutionizing various industries with cutting-edge AI solutions.

Jenkins agent (base image) and inbound agent Docker images

[IJCV 2024] InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions

Design notes for MyInvestPilot — an agent-friendly investment workflow system built with strategy primitives, DAG engines, validation loops, and observable decision infrastructure.

A C++/Python implementation of the StreetLearn environment based on images from Street View, as well as a TensorFlow implementation of goal-driven navigation agents solving the task published in “Learning to Navigate in Cities Without a Map”, NeurIPS 2018

把照片变成超现实波普拼贴的 AI agent skill：黑白现实锚点 + 平涂色形 + 全图只有一个不可能的巨物。An agent skill that turns photos into surreal pop collages.

Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.

Human-taught Computer-use Agent Designed for Real Windows and MacOS Desktops.

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms

An intelligent Wiki overlay tool designed specifically for gamers, featuring GEMINI-powered RAG (Retrieval-Augmented Generation) capabilities for smart Q&A services.

Your AI is trapped in apps. We set it free — Self-hostable AI stack for multi-user, multi-agent workflows on Matrix.

[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF / MAPF settings.

An enterprise-grade AI retriever designed to streamline AI integration into your applications, ensuring cutting-edge accuracy.

ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.

META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡

AI video production skill for agents: HeyGen avatars, Seedance b-roll, OpenAI images, Remotion, HyperFrames, screen recording, FFmpeg captions and QC.

YoLuster Shorts 釉光影：An independently developed AI short-drama creation workspace — from initial ideas to storyboard scripts, images, videos, and reusable asset management. Provides a Docker-based local demo package.

Open-source, bring-your-own-key (BYOK) multi-model AI chat client for iOS, Android and the web. One LLM client for OpenAI, Anthropic, Google Gemini, OpenRouter, DeepSeek and ten more providers, plus any OpenAI-, Anthropic- or Gemini-compatible endpoint — Ollama, LM Studio, llama.cpp, vLLM. Local-first, self-hostable, no account. AGPL-3.0.

CLIP⚡NCNN⚡基于自然语言的图片搜索(Image Search)⚡以字搜图⚡x86⚡Android

A next-generation AI-powered infinite canvas workspace built for creators and developers. Experience the future of Generative AI with a drag-and-drop node interface that combines Google Gemini 3 Pro, Veo 3.1, and LangGraph Agents into a seamless creative workflow.

Master AI inference, AI agent harness systems, and hardware engineering — then design a physical AI chip. That is the goal.

AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency.

《Agentic Design Patterns 智能体设计模式》 最佳中文版 pdf，中英文版本，持续优化，包含原文 + 中文批注，A Hands-On Guide to Building Intelligent Systems

1,000+ curated AI image prompts, including copy-ready JSON prompts for OpenAI image tools, product photography, portraits, character design, and more.

Open-source AI canvas design agent — alternative to Lovart / CapCut Video Studio / Canva AI. Chat-driven image & video generation on an infinite canvas.

Master AI BOT 🤖: Unleash the power of GPT-4 Turbo with our fast and limitless Telegram bot. Say goodbye to daily usage limits and laggy interfaces. Explore special chat modes, group chat support, and DALLE 2 integration. Chat seamlessly, recognize voice messages, and more. Deploy your own or use our streamlined version. Get started today! Demo 🔽

SharpToken is a C# library for tokenizing natural language text. It's based on the tiktoken Python library and designed to be fast and accurate.

AI-Powered Game Development Team in Your Terminal

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Your fully proficient, AI-powered and local chatbot assistant🤖

Open-source platform for multi-agent AI orchestration, real-world asset tokenization, workflow automation. Includes OAuth 2.1 MCP agent management, a 44-field RWA schema, Stripe, designed to integrate with AetherNet QUAS & KVS sovereign, post quantum, architecture agnostic omni-substrate, semantic memory, & institutional settlement system.

🤖 A Matrix bot for using different capabilities (text-generation, text-to-speech, speech-to-text, image-generation, etc.) of AI / Large Language Models (OpenAI, Anthropic, etc.)

An agent design team you control: 10 agents that run an inclusive design process while you direct.

A template for building WhatsApp agents using LangGraph and Twilio. This project enables you to deploy AI agents that interact with users via WhatsApp, process messages and images, and invoke custom graph-based agents. It integrates with MCP and runs on the LangGraph Platform.

AIFlow is an AI agentic framework designed to scale digital AI agents on BNB Chain.

(NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

Guide for designing adaptive, scalable, and secure enterprise multi-agent systems

a comprehensive and critical synthesis of the emerging role of GenAI across the full autonomous driving stack

AI agent skills for professional document generation (DOCX, PDF, XLSX) extracted from Kimi. Designer-quality outputs with native charts, validation pipelines, and full OpenXML control

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in one self-hostable stack.

Native Swift SDK for building autonomous AI agents with Apple's FoundationModels design philosophy

Beautifully designed components for building AI Agents 🌎

ZhiJuTong (ZJT) is an AI-powered, open-source platform specifically designed for creating professional short dramas. It automates the entire production pipeline, from script and storyboard creation to final video synthesis

Open-source, self-hostable LLM arena with model compare, voting, and leaderboards

LambChat — Enterprise Agent Infra for governed AI agents. Skills + MCP powered, Loop Agent ready, multi-tenant by design.

A local, multi-agent workspace designed like a messenger-style app. You can add custom teammates and chat with them individually, or create group chats and choose exactly which teammates to include. The whole experience feels like a familiar messaging app—but with much more powerful multi-agent collaboration capabilities.

Open-source 3D AI agent framework — GLB/glTF avatars with LLM brains, memory, emotions, and autonomous payments. MCP server · x402 · Solana/EVM · Three.js. Embed anywhere as a web component. Character studio, animation gallery, OAuth 2.1. Browser-native.

The model is the engine; the harness is the car. Curated knowledge on harness engineering — context management, tool design, agent loops, memory, sandboxing, evals. EN/中文

Generate images by Stable-Diffusion-webui Based on Python | 使用Python的基于 SD-webui 的画图机器人（支持中文、Novelai和Naifu）

Belullama is a comprehensive AI application that bundles Ollama, Open WebUI, and Automatic1111 (Stable Diffusion WebUI) into a single, easy-to-use package.

Self-hostable multimodal chat with local LLMs (Ollama/OpenAI): PDF RAG, image chat, and Whisper voice, Streamlit + Docker.

Implementation for the paper "ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems".

Comfy Cloud product skills: slash commands for generating images, video, audio, and 3D with Comfy Cloud agents. Single source of truth for the installer and MCP server.

从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill

NuGet package designed to make LLMs, RAG, and Agents first-class citizens in .NET

True on-device AI for Kotlin Multiplatform (Android, iOS, Desktop, JVM, WASM). LLM, Speech-to-Text and Image Generation — powered by llama.cpp, whisper.cpp and stable-diffusion.cpp.

AI pixel art agent that paints like a real artist. Not diffusion — actual tool-based painting with shapes, noise, and per-pixel control.

Self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.

高性能数字人桌面应用框架，开箱即用，集成了AI对话与动态壁纸，即使在较低性能的设备上也能流畅运行数字人

Easyreadme helps you simplify README creation and generate visually stunning ones with the help of AI and elegant pre-designed templates.

C++ Agent toolkit - Pre-built binaries, visit: https://github.com/mtconnect/cppagent/releases Docker images available at https://hub.docker.com/repositories/mtconnect

Fully automated token deployment on ETH, using ChatGPT and DALL-E.

NuGet package designed to make LLMs, RAG, and Agents first-class citizens in .NET

GPT/DALL-E-based ChatGPT-like chatbot that runs on both CLI and Telegram, with sharable imprints.

Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.

[archived] c4 GenAI Suite

GPT Image 2.5 prompts, verbatim and credited: 150 community prompts across 9 use cases, each with the author who wrote it and their post. Free to run.

Generate images & videos in the terminal, for humans & agents. Supports Google, OpenAI, ChatGPT sub, Fal, Replicate, SuperGrok sub, Seedance, Kontext

Browser script to share and export Anthropic Claude chat logs to Markdown, JSON, or as Image (PNG)

Algolia + Angular = 🔥🔥🔥

AI-driven web automation agent that uses Playwright for browser interactions and LLM integration for intelligent decision-making. It's designed for reliable, adaptable web automation with robust element detection and contextual understanding. It's single agent by design, and it is built with getting solid benefit out of smaller models in mind.

Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch & UForm AI Swift SDKs for Apple devices 🍏

Multi-Agent Team for Creating Long-form Videos

基于NineAi2.4.2的二开版本，含编译包和整合包，无需授权，全套源码，开箱即用，喜欢的给个Star~！

AI-powered assistant for EasyEDA — generate schematics from natural language, browse LCSC components, design PCBs with custom DRC configurations, and get interactive circuit design help.

Connect to hosted payram helper at: https://mcp.payram.com

The model is the engine; the harness is the car. Curated knowledge on harness engineering — context management, tool design, agent loops, memory, sandboxing, evals. EN/中文

Improve your questions! The AI for Inquiry - QuestionImprover Agent is an LLM-driven “tool for thought” designed to enhance the depth and quality of user-posed questions by engaging expert personas in a novel graph-based reasoning rhythm to foster a cycle of iterative inquiry improvement.

The shadcn for agent UI. A framework-agnostic design language for dense, AMOLED-black, multi-surface interfaces

Open-source Discord AI companion with ChatGPT-style conversations and image generation, now evolved into Erin.

A third-party component library based on Gradio. Integrates Ant Design, Ant Design X, Monaco Editor and more advanced components to help you build applications efficiently.

👷‍♂️High performance agent framework that can do everything. Minion is designed to execute any type of queries, offering a variety of features that demonstrate its flexibility and intelligence.

VividNode: Multi-purpose Text & Image Generation Desktop Chatbot (supporting various models including GPT).

AI生图工作台 (AI Image Generator)、视频工作台。支持 Agent 与工作台模式、无限画布、素材管理、提示词反推/广场及 PWA，支持外链式配置；可接入 Grok、GPT Image 2 等自定义模型生图。自适应手机端。

gguf quantized moe vlm vision agentic

Open-source document chat platform with semantic search, RAG (Retrieval Augmented Generation), and multi-provider AI support (OpenRouter, OpenAI, ImageRouter).

Machine Learning and having it Deep and Structured (MLDS) in 2018 spring

An open solution for AI-powered photorealistic digital humans.

🤖Free Agent Line Bot with Web Search, Google Image Search, Image Generator, Video Generator...

🧾✨ AI-Powered Receipt and Invoice Scanner for Laravel, with support for images, documents and text

Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, Modular design. Built-in voice & face recognition. Plug'n play tools. Compatible with ChatGPT, Claude, Deepseek, Gemini, Grok, and Ollama. Explore the possibilities of Human-AI Interaction.

The video editor built for AI. Create videos with React + TypeScript — designed for AI agents, LLM pipelines, and automated production. Fully open source.

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

To create a free AI Chatbot/Waifu/ Vtuber that will run on your local computer with minimal GPU requirement.

langchain 工具,流程设计组件,服务,代理以及相关学习文档的合集(agent,service,tutorials,flow-design)

iOS app that features a chat powered by ChatGPT and DALL·E 2

Open-source visual platform for AI agent and workflow development. Inspired by Coze & Langflow, built with Nuxt4, VueFlow, TypeScript, FeathersJS & Shadcn. Drag, connect, deploy — self-hosted and fully extensible by design.

小嘿作文生成器：根据主题谓语、主题宾语，生成中学考试风格的作文。