Open Source AI Models 175

Open-source 15B parameter AI model for joint video and synchronized audio generation. Happy Horse 1.0 is an advanced open-source AI video generation model designed to produce high-quality 1080p videos with synchronized audio and multilingual lip-sync capabilities. Developed by the Happy Horse team in 2026, it utilizes a 15-billion-parameter unified Transformer architecture to jointly generate video frames and corresponding sound from text or image prompts. The model is fully open-source, including weights and inference code, and is designed for self-hosting with full commercial-use rights. It features a unique 40-layer self-attention network that ensures stable training and cinematic output, making it a powerful tool for professional video production and localized content creation.

Document Management System for storing, organizing, and indexing scanned documents with search capabilities. Papermerge DMS is a Document Management System designed for digital archives. It allows users to store, organize, and index scanned documents in PDF, JPEG, and TIFF formats. The system features full-text search, tagging, and metadata-based search for quickly finding relevant information. It offers an open-source solution licensed under Apache 2.0, a user-friendly web interface, OCR capabilities, versioning, custom fields, category management, and page management.

Free, open-source AI image generator for rapid, high-quality image creation. Flux 1 AI is a free, open-source image generation model developed by Black Forest Labs, the creators of Stable Diffusion. It's designed for rapid image generation with exceptional prompt adherence, offering high-quality images that closely match user inputs. Flux 1 AI comes in three versions: FLUX.1[Schnell] for speed, FLUX.1[Dev] for developers, and FLUX.1[Pro] for maximum power.

A hub for open-source generative AI models and a community for AI art creators. Civitai is a platform dedicated to open-source generative AI, particularly focusing on Stable Diffusion and Flux models. It serves as a hub for creators to share AI-generated art, explore thousands of high-quality models, and engage with a vibrant community. The site features models, images, videos, and tools, and hosts challenges and events. It also includes an auction system for checkpoints, a buzz-based community engagement system, and showcases top creators in various categories.

Open-Source Self-Hosted AI Assistant OpenClaw AI is an open-source, self-hosted personal intelligence system designed to run on the user's local hardware (Mac mini, Windows, or Linux). It functions as an autonomous, action-oriented AI assistant focused on providing complete data sovereignty. It integrates with over 100 services and platforms, including messaging apps like WhatsApp, Telegram, Discord, and Slack, and supports various AI models such as Claude, GPT, Gemini, and local models. It is highly customizable via a modular skill system for automation tasks like email organization, calendar management, and system access.

Open-source platform to build, manage, and run autonomous AI agents. SuperAGI Cloud is a dev-first open source platform to build, manage, and run autonomous AI agents. It allows developers to build, manage, and run useful autonomous agents, offering features like concurrent AI agents, a marketplace for tools and agent templates, and agent performance monitoring.

A directory to find custom GPTs for ChatGPT. AllGPTs is a directory designed to help users find custom GPTs (Generative Pre-trained Transformers) for ChatGPT in one place. It serves as a comprehensive resource for discovering and exploring AI agents and applications that can be used within ChatGPT to enhance productivity and innovation. The directory is updated daily and allows users to browse by categories such as Design, Writing, SEO, Audio, and more.

Curated directory of open-source apps as alternatives to SaaS tools. Open Apps is a curated directory of open-source applications designed to provide free, open-source alternatives to popular SaaS tools. It offers a vetted selection of apps, ensuring quality and performance, and helps users find software solutions without the SaaS price tag. The platform categorizes apps by task and provides alternatives to specific SaaS products, making it easier for users to discover and implement open-source solutions.

Open-source tool for composing videos using HTML, CSS, and JavaScript. HyperFrames is an open-source framework, originally developed by HeyGen, that enables AI agents and developers to compose and edit videos using standard web technologies like HTML, CSS, and JavaScript. It introduces a 'Vibe-Coding' workflow where programmatic video creation is handled through code, allowing for high levels of automation and integration with AI tools. The project is licensed under Apache 2.0, making it accessible for the community to build upon and integrate into various workflows.

Local, privacy-focused memory app that captures and recalls digital activities using local LLM. reMind is a local, privacy-focused memory app that captures, indexes, and recalls your digital activities. With local processing, efficient indexing, and local LLM integration, reMind ensures your data stays private. Open-source for continuous improvement. It's a local Artificial memory for your device.

Local open-source Mac app providing live audio narration for AI coding agents. Agent FM is a local, open-source Mac application designed to provide ambient audio intelligence and live narration for your Claude Code and Codex AI agents as they work. It tracks agent progress, decisions, errors, and attention requests in real time, turning raw session outputs into spoken audio updates. Users can tune in to individual agent stations or listen to a Global Mix across all active agents.

Open-source AI code editor integrating AI tools for enhanced coding and project development. PearAI is an open-source AI code editor that natively integrates the best AI tools into a unified user experience. It curates and integrates AI tools for each layer of the AI coding tech stack, aiming to supercharge project development from inception to scaling. PearAI includes features like AI chat, PearAI Creator, and AI debugging, built upon foundations like Continue, Perplexity, Mem0, and Supermaven.

Genmo AI is an AI lab developing open video generation models using Mochi 1. Genmo AI is a frontier AI lab developing open video generation models. It allows users to create videos using AI, from text or images, using Mochi 1. The platform also showcases videos generated by the community.

Opensource voice-to-text macOS app with local AI for privacy and offline use. VoiceInk is an opensource voice-to-text app for macOS that transcribes what you say to text almost instantly with near-perfect accuracy. It uses local AI models to transcribe your speech to text, enabling offline functionality and ensuring data privacy. All data is stored locally, with optional AI enhancement.

House of Zoox offers Morphic, a free AI search engine, and Lumo AI, an open-source answer engine. House of Zoox is redefining search with Morphic, a free AI-powered engine that brings insights, images, and information to your fingertips effortlessly. It also mentions Lumo AI, a fully open-source AI-powered answer engine with a generative UI.

Platform for creators to receive donations, sell products, and engage with fans. Ko-fi is a platform that allows creators to receive donations and sales from fans of their content. It provides tools for creators to set up memberships, shops, and commissions, as well as widgets and integrations to help them earn more. Ko-fi also offers features like stream alerts and Discord integration to enhance creator-fan interaction.

Low-code platform for AI workflows with unified billing and access to diverse AI models. Gooey.AI is a low-code platform that allows users to discover, tweak, and compose AI workflows. It offers a unified billing layer for accessing various Generative AI models (e.g., OpenAI's GPT3 + DallE, Stable Diffusion, voice generators) and other APIs like social profile lookups and SEO APIs. Users can tweak workflows and use them as APIs in their own apps, prototyping AI integration with their sites/apps. It focuses on providing access to both private and open-source AI models.

Open-source AI tool for knowledge creation and organization in Obsidian. Text Generator is an open-source AI Assistant Tool that brings the power of Generative Artificial Intelligence to the power of knowledge creation and organization in Obsidian. For example, use Text Generator to generate ideas, attractive titles, summaries, outlines, and whole paragraphs based on your knowledge database. The possibilities are endless!

Open-source ecosystem building AR glasses with generative AI capabilities for developers and creatives. Brilliant Labs is an open-source ecosystem building pocket-sized AR glasses called Frame, powered by generative AI. It supports developers and creatives in reimagining the future with tools like arGPT, an iOS app for Brilliant Labs’ Monocle AR glasses, allowing access to generative AI chat applications and custom AI app development.

Novita AI: AI cloud with model APIs, GPU instances, and serverless GPUs. Novita AI provides access to over 100 APIs, including AI image generation and editing with 10,000+ models, and training APIs for custom models. It offers cheap pay-as-you-go services, freeing users from GPU maintenance hassles while building their own products. Novita AI also provides GPU Instances and Serverless GPUs for scaling AI, optimizing performance, and innovating with ease and efficiency.

Serverless AI inference provider offering a wide range of HuggingFace models with serverless pricing. Featherless is a serverless AI inference provider that offers access to a continually expanding library of HuggingFace models. It allows users to run any Llama model from HuggingFace without setting up servers, providing unmatched model range and variety with serverless pricing. It supports popular models for role-playing, creative writing, coding assistance, and more.

AI observability and evaluation platform for AI applications from development to production. Arize AI offers a unified LLM Observability and Agent Evaluation Platform for AI applications, from development to production. It provides tools for Generative AI, ML & Computer Vision, and Open Source LLM Tracing & Evals. Arize AX helps accelerate AI app and agent development and perfect them in production. It integrates development and production to enable a data-driven iteration cycle, using real production data to power better development and aligning production observability with trusted evaluations.

All-in-one chatbot client supporting multiple LLMs and offering various AI tools. ChatHub is an all-in-one chatbot client that allows you to use different chatbots in one app, currently supporting ChatGPT, Bing Chat, Google Bard, and Claude. It integrates more chatbots in the future. Features include conversation history, prompt library, code highlight, and more. It also offers tools like Image Generator, AI Translator, and Webpage Summarizer. It provides access to various AI models like GPT-4.1, Claude 3.5 Haiku, Gemini 2.5 Pro, and DeepSeek R1.

Open-source 3D asset generation model by Tencent. Hunyuan3D 2.0 from Tencent is an open-source 3D-DiT model for high-resolution 3D asset generation, including geometry and texture. It supports text and image to 3D asset generation using Diffusion technology. The model features text and image encoders, a diffusion model, and a 3D decoder, enabling multi-view generation, reconstruction, and single-view generation. It allows for the rapid generation of high-quality 3D objects suitable for various downstream applications.