Open Source Models

gpt-oss playground provides open-weight demos of gpt-oss-120b and 20b for infrastructure testing, distributed and on-device inference, benchmarking, API integration, and reproducible research, with adjustable reasoning levels and visible-reasoning for diagnostics. Demo-only; validate outputs.

FreedomGPT unifies access to 400+ AI models, showing side‑by‑side answers for voting and auto‑selection via leaderboard. It keeps privacy safe, runs on Windows/macOS, and is open‑source for community contribution and collaboration.

OpenRouter gives one API key to access 300+ models from 60+ providers, SDK‑compatible, with visual routing, automated fall‑back, edge hosting, data‑policy controls, and agentic tools for building efficient autonomous workflows.

OpenCreator is a generative AI workstation that integrates over 20 AI models for efficient content creation. With an intuitive interface, it enables quick visual production for various applications, including marketing and education, while simplifying the creative process.

Open Knowledge Maps is an AI search engine that visualizes scientific literature across disciplines, clustering related papers to reveal topic connections and trends. It supports varied document types, offers high‑quality metadata, multilingual browsing, and open‑source integration.

OpenArt is an AI art generator that provides powerful tools for you to generate and edit images, especially artist assets, that you can directly use and edit to improve.

OpenEvidence is a secure medical information platform for U.S. healthcare professionals, facilitating question logging, managing protected health information, and streamlining prior authorization letter writing with access to trusted clinical findings and insights from over 10,000 care centers.

OpenDream is a web‑based AI art generator that turns text prompts into images using models such as Dreamlike, Stable Diffusion, and Deliberate. It offers templates for logos, anime characters, and 3D objects, enabling rapid high‑resolution creations for commercial use.

Duck.ai offers anonymous access to popular AI models. It ensures privacy by keeping conversations untracked and outside AI training data, with seamless model switching.

Mistral AI offers developers a platform for building cutting-edge generative AI models with a focus on performance and customization. Their models excel in reasoning tasks and benchmarks, providing flexible deployment options across infrastructures.

DeepSeek Free provides browser access to 671-billion‑parameter DeepSeek-R1/V3 models for conversational Q&A, code assistance, math solving, and document/image-aware NLP; supports direct use without login, workflow integration, customization, and encrypted data handling.

Venice is a private on‑device AI platform that offers a broad array of open‑source models for text, image, code, and character creation. It includes a chat interface, an agent‑building API, watermark removal, upscaling, and batch image generation.

ModelOp is a centralized AI governance platform designed to manage enterprise AI initiatives, including generative AI and large language models. It offers automated compliance, real-time reporting, and risk mitigation tools, with over 50 integrations and customizable governance templates for streaml

Openkoda is an open‑source insurtech platform providing modular templates for claims, policy, and embedded insurance. It offers AI analytics, automated documents, role‑based access, multi‑tenant clustering, and API hooks for rapid, scalable development without vendor lock‑in.

OpenLIT is an open‑source observability platform for large‑language‑model applications, offering distributed tracing, real‑time monitoring, model evaluation, prompt versioning, fleet telemetry, and a zero‑code Kubernetes operator to integrate with major LLM providers and vector databases.

VModel provides a unified REST API that lets developers deploy and run custom or community‑built models with a single line of code. It supports Node.js, Python, and cURL for image, text, and video tasks, automatically scaling for production workloads.

OpenCraft AI is a secure, multi‑model copilot that unifies GPT‑4, Claude, and Gemini. It preserves context across model switches, keeps uploaded files accessible, auto‑formats chats into reports or decks, and generates images with consistent voice tone for streamlined workflows.

Flux LoRA offers a searchable library of low‑rank adaptation models for the FLUX image generation framework. Users can browse, compare, and download models, view usage statistics, and access FAQs and licensing information for compliant deployment.

Open‑Chat is a self‑hostable, decentralized chat platform that supports both proprietary and open‑source AI models. It provides a full chat API, runs LLMs on local GPUs, lowers latency, enhances privacy, and deploys easily on personal or cloud servers.

Bagel is an open-source multimodal model that enables advanced image and text processing, including generation and editing. It integrates image and text inputs for coherent outputs and supports tasks like chat generation and style transfer.

Falcon is an open‑source LLM family by the Technology Innovation Institute, spanning 0.09‑180 B parameters. It offers efficient Falcon‑H1 series, Arabic variants, multimodal Falcon‑3, and Falcon‑Mamba 7B, all under permissive licenses.

A free, user-friendly, multilingual, and open-source AI image generator that utilizes Stable Diffusion.

openmed is an on-device clinical AI platform for PHI/PII detection, de-identification, and healthcare NER, offering 1,000+ model variants, multilingual support, curated biomedical datasets, configurable privacy controls, and air-gapped macOS/iOS/server runtimes.

Open Apps is an open-source app directory that offers a curated selection of free alternatives to popular software tools, enabling users to find quality open-source solutions across various categories for development and productivity needs.

Inception Labs' diffusion-based large language models (dLLMs) offer faster, more efficient, and cost-effective text generation than traditional autoregressive models. With built-in error correction, multimodal support, and structured output control, they excel in function calling and complex data ge

Open Notebook is a self-hosted, open-source notebook for private LLM workflows, supporting over 16 AI providers. It enables multi-modal content management, vector search, and contextual chat with full data sovereignty for research and development teams.

Stable Diffusion Online lets users generate photo‑realistic images from text using the Stable Diffusion XL model. It offers fast GPU‑accelerated rendering, real‑time inpainting/outpainting, a 9‑million‑entry prompt database, and no prompt or image storage.

Pioneer automates retraining and deployment of open-source models, using live inference data for fine-tuning and one-shot adaptation. It manages adaptive inference, routing, RAG pipelines, agent workflows, synthetic data generation, monitoring, and automated checkpoint promotion.

Imagen is a generative AI model by Google DeepMind that produces high-quality, photorealistic images from natural language prompts using advanced diffusion techniques. It supports creative applications in design, media, and content generation.

Open‑source AI code‑review platform that plugs into GitHub, GitLab, Bitbucket, and Azure DevOps at the pull‑request level. Model‑agnostic, it runs custom rule sets, tracks technical debt, and delivers real‑time metrics without storing source code.

Img2Prompt is an AI tool that generates text prompts from images and provides a public API for image captioning and prompt-based image generation. It can run on personal hardware or cloud platforms.

LM Studio runs open‑source large language models locally on Mac (M‑series), Windows, and Linux, enabling private, offline inference. It offers command‑line and headless deployment, server‑side API, SDKs, a model hub, and LM Link for remote model access.

Rodin is an AI-powered 3D model generator that enables users to create high-quality assets using bounding box control and multi-view fusion. It supports integration with Unity and Unreal, along with features for texture generation and mesh editing.

JanusAI.Pro provides access to Janus pro model that enables unified multimodal understanding and image generation. It features high-resolution processing, lightweight design, and decoupled visual encoding pathways, optimized for efficiency with 1B and 7B parameter variants.

ownAI lets users build, host, and deploy custom AI assistants without coding. Create assistants for personal tasks, marketing, or support, with data hosted on your domain. Import knowledge bases, run models locally, and access open‑source code on GitHub.

Make-Print is an open‑source platform integrating Kanban project management, real‑time chat, and inventory control for 3D printing and CNC. It previews STL, OBJ, FBX, STEP, 3MF, GLTF files, auto‑calculates material costs, and lets teams customize via GitHub.

OpenAgents is an open-source framework for building and operating scalable, interoperable AI agent networks. It provides tools to launch, connect, and orchestrate agents with live monitoring, enabling collaborative applications and workflows.

ModelsLab offers API‑based generative AI for image, video, audio, and language tasks, including editing, generation, and voice synthesis. It supports GPU server deployment, custom workflows, fine‑tuning, and LoRA adaptation for creators and developers.

The Frontier Model Forum focuses on AI safety and responsible development by establishing standards and promoting collaboration among governments, industry leaders, and academia to address societal challenges and encourage ethical AI use.

MetaModels.ai transforms static product photos into high‑quality images and videos by draping them onto virtual models and styling options. Users pick models, outfits, and backgrounds, then receive human‑reviewed 4K‑ready files for e‑commerce and marketing.

Civitai is a community-driven hub for AI art and model sharing, offering a large gallery, model repository, and tools to create LoRA modules and Stable Diffusion checkpoints. Artists upload and remix images, while developers build and integrate custom models via API.

Open Voice OS is an open-source, community-driven voice AI platform for building customizable assistants across Raspberry Pi, embedded devices, Linux desktops, and Docker. It provides plugin-based STT/TTS, configurable wake words, extensible skills, and privacy-focused self-hosting.

RepublicLabs.ai generates images and videos with multiple generative models at once. No credit card or subscription is needed. Updated models let designers, creators, and marketers prototype visuals quickly across image and video workflows.

Miso One is a lightweight, open-weights 8B-parameter text-to-speech model optimized for expressive, low-latency conversational English speech. It enables real-time streaming, one-shot voice cloning, and 48 kHz exports for interactive voice agents and custom voiceover pipelines.

Modelfy 3D is an AI tool that converts 2D images into textured, production-ready 3D models. It automates the process from upload to export, delivering optimized assets for game engines, 3D printing, and design workflows.

Use.ai is an AI Workspace platform unifying access to over 25 AI models including ChatGPT, Claude, and Gemini, offering a single interface for versatile AI applications and seamless model switching.

Molmo AI is an open-source multimodal AI model for text and image processing, offering high-quality outputs on less powerful hardware. It enables easy integration, customization, and collaboration through a user-friendly dashboard for experimentation and analysis.

OSS Chat delivers a single chat interface that connects users to open‑source project resources—docs, issue trackers, papers, and community Q&A. It uses ChatGPT and a vector database to provide quick, privacy‑compliant access to up‑to‑date knowledge across diverse tech domains.

FiftyOne is a visual AI platform that centralizes data curation, annotation, and model evaluation across images, video, point clouds, and metadata. It offers interactive slicing, automatic labeling with confidence scoring, role‑based access, versioning, and open‑source integration.

Twenty.com is an open-source CRM and SDK for building customizable CRM solutions, offering modular objects, fields, relations, and TypeScript tooling for technical teams to extend, integrate, and deploy custom applications.