Open Source AI Models 395

Free, open-source full-stack SaaS boilerplate for faster development. Open SaaS is an open-source, feature-rich, full-stack React, NodeJS, and Prisma SaaS boilerplate template. It is designed to help users build and launch their SaaS applications faster by providing pre-configured essential features. These include authentication, payment integrations (Stripe/Lemon Squeezy), an admin dashboard with analytics (Plausible/Google Analytics), and built-in OpenAI integration for AI-assisted development. The template also supports AWS S3 for file uploads, email sending, a blog built with Astro, and offers full-stack type safety with TypeScript. It emphasizes no vendor lock-in, allowing deployment anywhere, and comes with comprehensive documentation, E2E tests, and community support.

A hub for open-source AI workflows with pre-configured templates and resources. Mozilla.ai’s Blueprint Hub provides tools to explore, collaborate, and build with open-source local models using pre-configured templates for common applications. It is a developer-first hub for open-source AI workflows, offering blueprints, building blocks, tools, datasets, and models to help users quickly start building.

Open-source platform for building, customizing, and deploying AI agents. OAK is an open-source platform designed for building, customizing, and deploying AI agents rapidly. It allows developers to connect to any LLM, extend functionality with plugins, and seamlessly embed AI into workflows. OAK is scalable, flexible, and built by developers for developers.

Open-source AI video generator with chunk-wise prompting for consistent, controllable video creation. MAGI-1 is an open-source, autoregressive AI model for video generation developed by sand-ai. It offers high temporal consistency and controllable generation through chunk-wise prompting. MAGI-1 generates videos by predicting sequences of video chunks, ensuring smooth and consistent output with fine-grained control. It supports features like image-to-video conversion and physics simulation.

Alibaba's free open-source AI image generator excelling at text rendering for marketing visuals. Qwen Image is Alibaba's free open-source AI image generator that excels at text rendering in images. It is designed to solve the biggest problem in AI-generated marketing content: readable text in images. It is free for commercial use, open source, and customizable, offering features like perfect text rendering in any language (English & Chinese), high-resolution output (up to 1328×1328 pixels), advanced image editing, and lightning-fast generation. It aims to provide cost savings, time efficiency, and global reach for marketers and content creators.

AI-powered image editing model with semantic, appearance, and text editing. Qwen-Image-Edit is a revolutionary 20B parameter AI image editing foundation model released by Alibaba's Qwen team. Built on the Qwen-Image generative model, it extends unique text rendering capabilities to image editing, enabling precise editing of Chinese and English text. The model features high-level semantic editing and appearance editing capabilities, offering a comprehensive solution that significantly lowers the barriers to image content creation and modification. It is open-source under the Apache 2.0 license.

AI-driven code intelligence models for software engineering and coding tasks. Kat Dev is an AI-driven code intelligence offering developed by Kuaishou's Kwaipilot team. It is a family of large language models specialized for software engineering and coding tasks, designed to act like AI engineers. Kat Dev models are capable of understanding complex requirements and generating high-quality code, achieving high performance on benchmarks like SWE-Bench. The models are high-parameter LLMs (32B or 72B) trained specifically for coding with state-of-the-art architectures and extensive reinforcement learning, including multi-stage agentic training with tool use, multi-turn dialogue, and coding knowledge.

First open-source 4K AI model for synchronized video and audio generation. LTX-2 is a state-of-the-art, production-ready AI foundation model developed by Lightricks for generating synchronized audiovisual content. It is the first fully open-source, open-weights AI model that supports native 4K resolution (2160p) video generation at up to 50 FPS, along with synchronized audio generation (including dialogue, ambient sounds, and music). Powered by a 19B parameter Diffusion Transformer (DiT) architecture, LTX-2 supports text-to-video and image-to-video generation, creating clips up to 20 seconds long. It is optimized for NVIDIA GPUs, offering 3x faster performance on RTX 50 Series.

State-of-the-art open-source AI image generator excelling in text rendering and knowledge. GLM-Image is a state-of-the-art open-source AI image generation model developed by Z.AI (Zhipu AI). Released under the Apache-2.0 license, it features a groundbreaking hybrid architecture combining a 9B-parameter autoregressive transformer with a 7B-parameter diffusion decoder. This architecture allows it to achieve industry-leading performance in precise text rendering (0.9116 CVTG-2K accuracy) and knowledge-intensive content generation, supporting high resolutions up to 2048×2048. The glm-image.top site operates as an independent service deploying and optimizing these open-source models.

Self-hosted, open-source AI assistant with persistent memory and system actions. Moltbot AI (formerly Clawdbot) is an open-source, self-hosted personal AI assistant that performs actions beyond standard chatbots. Known as 'Claude with hands,' Moltbot addresses the weaknesses of conventional AI by offering persistent memory stored locally, proactive communication (reaching out first via chat apps like Telegram/WhatsApp), and complete system-level execution capabilities with Shell privileges for file handling, program execution, and web browser control. It runs on Mac, PC, or Linux and ensures absolute data privacy by keeping all information on the user's device.

745B parameter AI model built for agentic intelligence and frontier-level reasoning. GLM-5 is Zhipu AI's fifth-generation large language model, featuring a massive 745 billion total parameters and 44 billion active parameters in a Mixture of Experts (MoE) architecture. Developed as a spin-off from Tsinghua University, GLM-5 is engineered for agentic intelligence, frontier-level reasoning, and advanced coding capabilities. A standout feature is its full hardware independence, having been trained entirely on Huawei Ascend chips using the MindSpore framework. It serves as a direct, cost-effective challenger to global models like GPT-5 and Claude, with a strong focus on open-source availability and long-context processing through DeepSeek's sparse attention mechanism.

100% local, private AI assistant that runs entirely on your own hardware. ZeroClaw is an open-source, private AI assistant designed to run 100% locally on a user's hardware. Built with a focus on security and performance using Rust, it allows users to deploy autonomous agents without relying on cloud services or subscriptions. The platform ensures that data never leaves the local machine while providing integrations with popular messaging platforms like Telegram, Discord, and WhatsApp. It features a lean runtime with a memory footprint of less than 5MB and a trait-driven architecture that makes it easy to swap providers, tools, and memory implementations.

AI-powered, open-source CSV importer for SaaS and standalone use. YoBulk is an AI-powered, open-source CSV importer designed for SaaS applications and standalone use. It offers a simple way to create import templates, enabling users to import and transform CSV files into a smart spreadsheet interface. YoBulk supports large-scale CSV validation, leveraging OpenAI for advanced column matching, data cleaning, and JSON schema generation. It allows developers to create custom CSV importers with personalized validation rules, ensuring data privacy and control.

Open-source AI journal providing insights and resources using AI. Gnothi is an open-source AI journal that provides insights and resources. It leverages GPT-powered prompts using entry history as context, behavior analysis, book recommendations, entry summaries, and recurring themes.

Recap is a Chrome extension that uses ChatGPT to summarize webpage sections. Recap is a Chrome extension that utilizes ChatGPT to summarize webpages. Compared to other existing extensions, Recap's main feature is to split content into passages, allowing users to summarize specific sections of an article, rather than the entire text.

AI-driven project management platform for AEC sector, organizing unstructured data. MDLR is an AI-driven project management platform for the AEC sector, combining 3D model annotations, dashboard insights, and automated delivery setups for streamlined collaboration and data-driven decisions. It's an open-source framework that analyzes unstructured content to organize scattered data into actionable summaries, adapting to personal and collaborative projects.

Predicts and prevents supply-chain attacks via metadata-driven analysis. Trace-AI is a platform designed to predict and prevent supply-chain attacks. It achieves this through metadata-driven analysis of open-source dependencies, registries, and maintainer activity, without requiring access to source code. The service provides real-time Software Bill of Materials (SBOMs), exploit-aware risk scoring, license compliance, and vendor visibility. Built by experienced engineers, Trace-AI aims to help teams ship fast and securely, offering transparency through its open and auditable ZSBOM model.

Open-source tool for building document question-answering systems with local AI models. RLAMA (Retrieval-Augmented Local Assistant Model Agent) is an open-source AI solution that integrates with local AI models to create, manage, and interact with Retrieval-Augmented Generation (RAG) systems. It allows users to build powerful document question-answering systems with multiple document formats, advanced semantic chunking, and local storage and processing.

All-in-one LLM App Platform for building, deploying, and optimizing Generative AI apps. Klu is an all-in-one LLM App Platform designed to help AI Engineers and teams build, deploy, and optimize Generative AI applications. It provides tools for collaborative prompt engineering, automatic evaluation of prompt and model changes, 1-click fine-tuning of models, and seamless integration with various data sources (databases, files, sites) and best-in-class LLMs (Claude, GPT-4, Llama 2, Mistral, Cohere, etc.). Klu aims to enable rapid iteration, understand user preferences, and curate data for custom models, ultimately helping businesses create unique AI experiences and competitive moats.

A.I. developer bots for web application generation and code migration. Second provides A.I. developer bots that can generate new web applications or add full-stack features to existing ones. It offers automated code migrations for developers, leveraging OpenAI, Azure OpenAI, AWS Bedrock, and open-source models. Second agents are controlled by purpose-built modules engineered for specific code migrations, eliminating prompt drift. They are experts in the latest versions of modern frameworks and libraries and interface with human developers via GitHub, Bitbucket, or Gitlab pull requests. Second agents fully migrate and upgrade codebases, including dependency resolution, updating build systems, and updating tests.

ChatTTS is a voice generation model for conversational scenarios in Chinese and English. ChatTTS is a voice generation model designed for conversational scenarios. It is ideal for applications such as dialogue tasks for large language model assistants, as well as conversational audio and video introductions. The model supports both Chinese and English, demonstrating high quality and naturalness in speech synthesis. This level of performance is achieved through training on approximately 100,000 hours of Chinese and English data. The project team plans to open-source a basic model trained with 40,000 hours of data, which will aid the academic and developer communities in further research and development.

Msty simplifies AI model usage with offline support, split chats, and a unified interface. Msty is an AI application designed to simplify the use of AI models. It offers features such as private and offline functionality, split chats, branching, concurrent chats, web search, RAG, a prompts library, and more. It aims to be a Perplexity, Jan AI, and LM Studio alternative, allowing users to use models from OpenAI, Deepseek, Claude, Ollama, and Hugging Face in a unified interface.

AI creative platform for text-to-video, image-to-video, and image generation. ArtAny AI is an AI creative platform that enables text-to-image, image editing, text-to-video, and image-to-video creation. It features advanced models like Wan 2.2, developed by Alibaba Wan AI (Tongyi Lab), which is a leading AI video generation model. Wan 2.2 excels in generating high-quality videos from text, images, and other control signals, supporting complex motions, physical simulations, cinematic quality, and visual text generation in both Chinese and English. The platform aims to provide a user-friendly experience for leveraging these powerful AI models.

Magical AI image generator for stunning art. Z Image Turbo AI is a magical AI image generator designed to create stunning AI images in seconds. It aims to make art fast, easy, and delightful for artists, creators, and anyone with imagination. The platform allows users to turn their imagination into beautiful images using the Z Image Turbo model. It features a live prompt box for instant preview of results before committing to a plan or download. Z Image Turbo boasts super-fast generation, stunning photorealistic quality, simple natural language prompting, multilingual understanding (English, Chinese, etc.), and flexibility to be used in a browser or run locally. While the underlying model is stated to be open source and free for personal or commercial projects, the hosted service operates on a credit-based system with various pricing plans.