Image agents

OpenAI Gym environment designed for training RL agents to control the flight of a two-dimensional drone.

Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.

gradio region:us

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

An AI-powered agent based framework designed to assist with complex software engineering tasks

Policy Synth is a TypeScript class library designed to streamline and enhance decision-making processes through multi-scale AI agent logic flow.

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)

modular, service-oriented CAD

🌟 Revolutionize Your Operations with One Sentence Automation: Utilizing large language models and Multi-Agents to generate operational copy, images, and videos with one-line requirements.

An ecologically inspired multi-agent system. Agents are designed with neural network based decision making, and complex resource requirements.

Agent Innovator Lab – building AI agents on Azure, covering search optimization, agent design, evaluation, and RAG best practices.

The first platform designed to empower organizations by automating and enhancing their employment processes through advanced autonomous agents.

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-scoped and safe by design. Complementary to MCP. Paper: arXiv:2605.26159

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

Agent Skill that makes Claude a pixel artist — no Aseprite, no MCP, no diffusion. Every pixel is a decision.

Your Digital Companion. Self-hosted Telegram bot orchestrating multiple AI providers (OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral, Alibaba, MiniMax) with autonomous agent capabilities, MCP integrations, and async task execution. Not a tool. A partner.

This repository provides an OpenAI Gym-compatible environment for production scheduling tasks, designed to benchmark reinforcement learning agents in job shop and flow shop settings.

Generate Google Stitch compatible DESIGN.md files from any website using AI vision. Bring your own Gemini, OpenAI, Claude, or Ollama key. No backend, no cost.

⛩️🌸 Meet Ririko AI, a powerful AI-powered Discord bot with Twitch Live Notifier, Reaction Roles, Giveaways, OpenAI, Stable Diffusion, Moderations, Anime / Manga Finder and more features. A Discord bot you can call your companion! Based on Discord.js v14. By @earnestangel

Build multi-model chatbots and agents from intent.

Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale from ingesting large amounts of documents formats such as pdfs, docx, xlsx, png, jpgs, tiff, mp3, mp4, jpeg. Integrates with s3, Windows Shares, Google Drive and more.

【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Awesome GPT Image 2 Prompts

chatgpt nodejs服务，集成了ChatGLM、GPT3.5、GPT4、GPT联网、必应、Claude、百度文心一言等模型

UcxUcc is a simple but powerful team collaboration suite of applications designed to improve communications, information sharing and productivity for the businesses small and large.

openai notionai chatgpt 免费chatgpt资源整理 MidJourney关键词 prompt chatgpt代理配置

An autonomous photonic device design agent iteratively optimizes silicon photonic devices — no human in the loop.

Private local AI Photographer Agent on AMD Radeon and ROCm

An LLM that plays RimWorld and rewrites its own playbook between colonies. RimBridge mod + self-improving agent.

Fibo is a cutting-edge framework designed to build and deploy AI agents that seamlessly integrate automated task execution with interactive chat capabilities.

This project contains a step-by-step guide on how to design an advanced agentic memory for your LLM based applications.

Electron + Next.js desktop AI assistant that runs GGUF models locally using llama.cpp. Designed for offline use, portability, and zero-install deployment.

DeepSeek Harness 便携桌面版：免配运行环境、内置插件市场、工作环境随行，Portable 与内核独立更新。支持 Windows、macOS、Linux。

Turn any document into ready-to-use AI image prompts.

A cutting-edge AI SaaS platform that enables users to create, discover, and enjoy podcasts with advanced features like text-to-audio conversion with multi-voice AI, podcast thumbnail image generation, and seamless playback. The platform is built using Next.js, TypeScript, Convex, OpenAI, Stripe, Clerk, ShadCN, and Tailwind CSS.

An autonomous AI agent written in Go, designed to run entirely on the 32MB RAM of an obsolete OpenWrt router. It acts as an always-on smart home orchestrator with Wake-on-LAN, Telegram, and Google Workspace integration.

🔥 Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents

Agent-native CLI for Adobe InDesign automation — 150 tools, HTML ↔ InDesign conversion, and structured JSON returns built for AI agents.

AI-powered infinite canvas — aggregate multiple AI platforms for image & video generation, LLM chat, and ComfyUI workflow execution. Built-in Agent system with knowledge bases, custom Python skills, and encrypted distribution. Connect your local ComfyUI backend for seamless workflow automation. Zero-config LAN collaboration with bilingual UI.

This is a collection of AI ecosystem, which gathers and organizes various interesting and useful AI-related projects

Free AI skill pack for senior UX and Product Designers. Runs on Claude Projects or any LLM. Strategic, Direct, and Provocative reasoning modes. Copy, paste, done.

A community-maintained collection of resources for economists applying microeconomic theory, game theory, econometrics, industrial organization, and behavioral economics to the development of AI systems: post-training, alignment, safety, mechanism design for AI, and multi-agent systems.

LLM Powered discord bot, Character Card enabled Chat page, Stable Diffusion discord bot, and overall AI tool. All from one app, TalOS.

Agent Based Class Design

AI-powered visual novel generator

PromptBar is a SwiftUI application designed for macOS, allowing users to access multiple AI chats directly from their menubar. This app provides a convenient way to interact with the multiple AI chats without needing to open a browser or switch between applications.

CLI tool for Turkish legislation (mevzuat.gov.tr). Designed for AI agents and programmatic use.

[AAAI 2026 Oral] Automatic Multi-agent Communication Topology Design

[ACL'26 Oral] AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression

LLM skill for designing with OpenPencil via the op CLI and MCP tools

Open-source, self-hostable, zero-knowledge memory for AI agents. End-to-end encrypted — the server stores only ciphertext and can't read your agent's memory. Works with any MCP agent .

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, REST/SSE, and MCP.

A muted, poetic paper-poster Agent Skill for low-saturation zine-style image generation.

This is a professional CV template inspired by the legendary secret agent James Bond. BubbleCV is designed to effectively showcase your skills, work experience, education, and contact information in a sleek and impactful manner.

Source-reading field guide for Pi Agent Harness: architecture notes, design breakdowns, and experiments.

A telegram bot based on large language models (GPT-3) for image tasks like creating image, captioning, editing and general conversation like chatting about images based on stable diffusion, huggingface and langchain.

This package can be used to connect Telegram bot to AI engines such as OpenAI ChatGPT, Dall-E, Midjourney, Stable Diffusion, etc.

Agent Studio is an AI agent application designed to handle real-time interactions through phone calls, web-based voice user interfaces (VUI), and SIP capabilities.

An agentic AI assistant built with Rust 🦀 , inspired by OpenClaw, NanoClaw, NullClaw, ZeroClaw, and MicroClaw and incorporating some of their design ideas. Contributions welcome!

DaveLovable The Most Advanced Open-Source AI Web Development Platform Build React applications at lightning speed with AI-powered multi-agent orchestration

Open-source AI Agent platform — 80+ MCP tools, 7 channels (Slack/Discord/LINE/Telegram), Rust + Python. Self-hostable Claude/GPT alternative for production multi-LLM systems.

A curated collection of actuarial AI case studies covering machine learning, generative AI, agentic AI, and more, designed to support actuaries in applying AI to real-world problems.

Agent Skill: turn a character image into a looping transparent sticker pack (WebP/GIF/PNG + ZIP).

Your logo, as your agent's loading animation. Bake any SVG into a dot cloud and play it as seven AI loading states.

半调纸拼贴风信息动画 Agent Skill · Halftone paper-collage info-graphic animations from voiceover scripts (HyperFrames, no image models)

A responsive U.I design plugin for your rasa chatbot.

​Meow meow, dis iz a GitPurr repository of CatGDP fur feline whiskerful conversations. Pawsome, right? Hiss-tory in the making! Happy Caturday! 🐾

GitHub CLI for agents — designed with AXI (Agent eXperience Interface).

Robust skills for Agents

3D virtual room where AI agents walk, chat, and collaborate as animated lobster avatars

This repository aims to implement an Image Search engine powered by the CLIP model.

👻 kwami.io | A 3D Interactive AI Companion Library for creating engaging AI companions with visual (blob), audio, and AI speech capabilities.

Multi Aarch image of iSpy's Agent DVR, standalone free-to-use NVR software for IP Camera management

Local-first, AI-assisted circuit design tool. Wire components in a 3D view, describe what you want to build, and the AI agent writes the firmware and simulates it all before you touch a chip.

IEEE JBHI 2026 | MedSegAgent: A Universal and Scalable Multi-Agent System for Instructive Medical Image Segmentation

Advertising prompt agent for Image2: turns business briefs and reference images into debranded, production-ready image prompts.

MCP server for Meshy AI 3D generation platform

Simple docker sandbox image for Hermes Agent

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing deep hardware intelligence.

SoccerLab is designed for developing, training, and deploying advanced control strategies for legged robots in a dynamic, multi-agent soccer environment.

Visual agent design platform for embodied AI — prototype agents as typed node graphs that execute against simulators in real time.

Hermes Agent weather plugin — NWS-grade model imagery, NEXRAD radar, and verified meteorological calculations. Pure Rust stack.

Designed for managing vulnerability discovery at scale with agentic AI and integrates with HackerOne.

A self-hostable, model-agnostic realtime voice layer for personal PWA and terminal agents.

Director Agent + vision critic + image, video, music & voice models - all on a single AMD Instinct MI300X.

Explore the image embeddings of Unsplash using CLIP's image similarity

This repository contains a web application designed to execute relatively compact, locally-operated Large Language Models (LLMs).

GoCD Agent Docker image

Enterprise-grade MCP Server for FHIR-based EMRs, designed for robust deployments in agentic AI platforms.

智能体系统设计与实战：基于langchain与langgraph，Agent System Design and Practical Applications: Based on LangChain and LangGraph

Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.

transformers gguf quantized vlm vision agentic

Give AI agents the power to read Cadence, Altium, and KiCad designs

Hades is a fully-featured cross-platform Chrome Extension agent. Hades is designed for Mythic 3.0 and newer.

An eve agent to act as your design collaborator

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 settings.

AAAI 2025: Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation

Real Estate AI property valuation

Experience the power of Clarifai’s AI platform with the python SDK. 🌟 Star to support our work!