Open Source AI Models 395

Platform for simplified ML model deployment, scaling, and inference via a unified API. WizModel is a platform designed to simplify the deployment and scaling of machine learning models. It provides a unified API for ML inference, allowing users to run models without extensive coding. WizModel offers tools like Cog2 to package models into production-ready containers and automatically generates scalable API servers, handling dependencies, GPU configurations, and scaling. It also allows users to explore and use thousands of pre-existing models shared by the community.

A free website to chat with Meta's Llama 4 Maverick AI model. Chat With Llama is a free website that allows users to talk with Meta's latest AI models. Currently Meta's latest model is the 17 billion parameter Llama 4 Maverick. This model is comparable to GPT-4o and Gemini 2.0. Using Chat With Llama, you are able to test the model completly for free. This gives developers a look as to what the model is capable of. Llama 4 Maverick is a new 17 billion parameter model developed by Meta. Llama 4 was released on April 5, 2025 and is the most powerful chat model yet. It is able to beat both Gpt-4o and Gemini 2.0. Likewise, as with all previous models Llama 4 is open source so users are able to train their own version and use it commercially.

Global cloud platform for AI training, offering an easy-to-use SDK and cost-effective GPUs. Lumino is a global cloud platform designed for AI training and development. It offers an easy-to-use SDK for developing and training machine learning models, aiming to lower ML training costs by up to 80%. Lumino provides access to GPUs that may not be available elsewhere, enabling users to fine-tune LLMs like Llama 3.1 with just a few lines of code, without the need to set up compute instances or build ML infrastructure.

Open-source enterprise AI agent platform for secure, scalable task automation. NemoClaw is an open-source enterprise-grade AI agent platform launched by NVIDIA, designed for secure deployment, privacy protection, and scalable task automation. It deeply integrates with the NVIDIA NeMo framework, Nemotron model series, and NIM (NVIDIA Inference Microservices) to provide efficient AI inference and training. Unlike many proprietary solutions, NemoClaw features a hardware-agnostic architecture, allowing enterprises to build and deploy AI agents not only on NVIDIA GPUs but also on hardware from AMD, Intel, and other providers. It aims to provide a controlled environment for sensitive data and mission-critical workflows, bridging the gap between personal AI assistants and regulated enterprise requirements.

Enterprise-grade aggregator providing unified access to 500+ AI models via one API. FunnySkill-API is a comprehensive AI interface service platform designed for developers and enterprises. It offers a stable, high-concurrency, and low-latency solution by integrating over 500 large-scale AI models from global providers like OpenAI, Anthropic, Google, and DeepSeek. The platform acts as a unified hub, providing one-stop access to text, image, audio, and video generation capabilities through a single API protocol that is fully compatible with OpenAI standards. It features advanced architecture for high availability, transparent billing, and a variety of specialized model groups to meet diverse business needs ranging from simple data processing to complex autonomous agent tasks.

Unified AI model generating high-quality video and audio from text or images. Happy Horse AI is an advanced AI video generation platform powered by the Happy Horse 1.0 model. It utilizes a unified self-attention Transformer architecture to jointly generate high-quality video and audio from text or image prompts. Unlike traditional multi-stream pipelines, it denoises text, video, and audio tokens in a single pass, enabling physically realistic multi-shot videos with native lip-sync and spatial sound effects. It is designed to be blazing fast, multilingual, and fully open-source, catering to creators who need cinematic 1080p content quickly.

Open-source, self-hosted personal AI assistant with 100+ integrations and full privacy control. Clawdbot AI is an open-source, self-hosted personal AI assistant designed to run on the user's own device (Mac mini, PC, or Linux). It is proactive, capable of taking actions such as clearing the inbox and managing the calendar. It features extensive integration with over 100 platforms, including messaging services like WhatsApp, Telegram, Discord, and Slack, and productivity tools like Gmail and Google Calendar. Clawdbot offers full privacy control, ensuring all data remains local. It supports multiple AI models (Claude, ChatGPT, Gemini, or local models) and features an extensible architecture allowing customization via community or custom-built skills for web and deep system automation.

Open Source BaaS for AI apps to securely call LLM APIs without backend. Backmesh is an open-source Backend as a Service (BaaS) designed for AI applications. It provides a secure way to call LLM APIs from your app without exposing private keys or requiring LLM SDKs. Backmesh offers features like JWT authentication, rate limits per user, and API resource access control to ensure secure and efficient LLM API usage. It also includes LLM user analytics to help identify usage patterns, reduce costs, and improve user satisfaction.

Open-source, self-hosted AI assistant that executes tasks across multiple chat platforms. Moltbot is an open-source, self-hosted personal AI assistant designed to execute tasks autonomously across various messaging platforms, including WhatsApp, Telegram, Discord, Slack, and iMessage. It integrates with over 50 services (like Gmail, GitHub, Calendar, and Spotify) and is built with a privacy-first approach, allowing users to run the assistant on their own infrastructure (Mac, Windows PC, or Linux server). Moltbot functions as a proactive agent that remembers context and adapts over time. It is model agnostic, supporting cloud models like GPT-4 and Claude, as well as fully local models via Ollama for zero cloud dependencies. Moltbot is the active development evolution of the previous project, Clawdbot.

Chat with LLaMA, Alpaca, and GPT4All models locally on your Mac. LlamaChat is an application that allows users to chat with LLaMA, Alpaca, and GPT4All models locally on their Mac. It supports importing raw PyTorch model checkpoints or pre-converted .ggml model files. LlamaChat is open-source and free to use, powered by libraries like llama.cpp and llama.swift.

AI image generator and editor specialized in bilingual text rendering. Boogu Image Generator is an online browser-based workspace built around the Boogu-Image-0.1 open-source unified image generation and editing model family. It allows users to perform text-to-image creation, fast Turbo drafting, and instruction-style image editing workflows without requiring local GPU setups. The platform features Base, Turbo, Edit, and FP8 model variants, and is highly optimized for practical Chinese-English bilingual text rendering, poster designs, interface mockups, and product visuals.

Open-source platform for designing, deploying, and monitoring AI workflows. Draft'n run is an open-source AI agent platform that empowers teams to design, deploy, and monitor AI-powered features and production-ready AI workflows faster than ever. It transforms complex AI integration into an intuitive, visual process with full transparency, control, and scalability. The platform enables developers, product teams, and software and AI agencies to build production-ready AI workflows without code, including AI chatbots, automated workflows, and agentic AI, with built-in DevOps, observability, and governance. It features a drag-and-drop Studio for building workflows, an interactive Sandbox for testing, comprehensive Observability for monitoring, and REST APIs for integration.

Open-source AI chatbot builder for creating and managing AI-powered chatbots. Hexabot is an open-source AI chatbot builder that allows users to create and manage AI-powered chatbots and agents without complex coding. It offers an intuitive platform to build engaging chatbots that enhance customer satisfaction and drive business growth. Hexabot supports multilingual chatbots, various chatbot plugins, and multi-channel deployment, making it easy to manage customer experience across different platforms.

AI chatbot builder for websites, providing instant and accurate customer support. WebWhiz allows you to create an AI chatbot that knows everything about your product and can instantly respond to your customer's queries. It's a ChatGPT for your website, enabling you to launch an AI-powered assistant that delivers instant, precise responses to support queries. WebWhiz provides data-specific responses, ensuring accuracy, and offers regular data updates by crawling your website. It supports 100+ languages and prioritizes GDPR compliance.

Open-source platform for building, connecting, and orchestrating AI Agent Networks at scale. OpenAgents is an open-source project dedicated to building and scaling AI Agent Networks. It provides the necessary framework and open protocols for developers to launch and join large networks, enabling thousands of AI agents to connect, collaborate, learn, and tackle complex challenges within a single community. The platform is designed for maximum interoperability, integrating with leading LLMs, various protocols (like WS, gRPC, HTTP), and popular agent frameworks (LangChain, AutoGen, Camel AI).

SDXL Turbo is a fast text-to-image model using Adversarial Diffusion Distillation (ADD). SDXL Turbo is an advanced generative text-to-image model that employs Adversarial Diffusion Distillation (ADD) for training. It is a faster and distilled version of SDXL 1.0, capable of synthesizing high-quality, photorealistic images from a text prompt in just one network evaluation. SDXL Turbo's key innovation lies in reducing the required step count for image generation from 50 to just one, enabling real-time synthesis with unprecedented image quality.

Offline AI app for iPhone, iPad, and Mac, ensuring total privacy and customizable AI models. Privacy AI is a mobile and desktop application that allows users to run advanced AI models offline, ensuring complete data privacy. It features models like LLaMA, Mistral, Phi3, StableLM, and Gemma2, with customizable settings for fine-tuning interactions. The app is available for iPhone, iPad, and Mac, offering both free and premium options, including a one-time purchase model.

Niddam provides private AI tools and LLM products to enhance workflow and protect privacy. Niddam is an AI company focused on providing LLM (Large Language Model) products and tools that enhance workflow and respect user privacy. It offers a private AI experience, allowing users to engage in natural-sounding conversations, generate high-quality content, summarize documents, and resolve creative challenges without sacrificing their data security. Niddam aims to empower users with AI capabilities while maintaining control over their personal information, offering an alternative to Big Tech solutions.

Leading AI model providing instant AI solutions. DeepSeek-v3 is a leading DeepSeek AI model and cutting-edge AI solution powered by advanced MoE architecture and state-of-the-art language models. It provides access to instant AI solutions, offering free access to a stable and intelligent model without limitations. DeepSeek-v3 stands out with its innovative Mix-of-Experts architecture, extensive professional training, fast and efficient output, and support for multiple languages and deployments.

Amanu builds Telegram apps for AI startups, offering fast MVP development and AI infrastructure. Amanu is a company that specializes in building Telegram apps for AI startups, offering services such as chatbots, mini apps, and AI infrastructure. They provide a guided journey from idea to MVP in just 4 weeks, helping AI startups quickly tap into Telegram's vast user base.

Open-source, uncensored AI platform for 4K video generation with synchronized audio. Vidthis AI is a professional, AI-powered platform for video and image generation, featuring the flagship LTX-2 model. LTX-2 is an open-source, uncensored AI model specializing in production-grade 4K video generation (up to 50 fps and 20 seconds duration) with perfectly synchronized audio. It offers high creative freedom, supports LTX 2 LoRA for director-level control over camera movements and character consistency, and includes various other advanced models like Wan 2.5, Hailuo 23, and Nano Banana Pro for all-in-one content creation needs.

Open-source, natural-language CLI for AI-powered, code-free browser automation. BrowserBash is an open-source, plain-English command-line interface (CLI) tool designed for AI-driven browser automation. It allows users to execute complex browser actions by describing them in natural language, eliminating the need for manual selectors, code, or flaky locators. BrowserBash supports various execution environments, including local Chrome, Browserbase, LambdaTest, and BrowserStack. It operates on either local models via Ollama or cloud models via OpenRouter, ensuring no API keys or credit cards are strictly required to start. The tool is built for CI/CD integration, offering features like NDJSON output, session recording, and the ability to run automated tests as simple Markdown files.

Unified AI chat platform accessing 16+ premium models like GPT-5.4 and Claude under one subscription. NottoAI is an all-in-one AI platform that provides access to over 16 premium artificial intelligence models through a single chat interface and one subscription. It allows users to use advanced models like GPT-5.4, Claude Opus, Gemini Pro, DeepSeek, and Grok without paying for multiple individual services. The platform features the ability to switch models mid-conversation to compare answers, integrated web search for real-time data, and support for file uploads. Users can also bring their own API keys for more control, while the service ensures conversation history is saved and searchable across all models.

Open-source platform for AI-powered mobile app automation and data extraction. Droidrun transforms Android devices into an AI playground, enabling users to create and control autonomous agents across native mobile apps. It provides AI with native control over mobile applications and phones, allowing for the automation of mobile workflows and the unlocking of data from any app. Droidrun is 100% open-source and is designed for testing, automation, and experimentation, with a cloud-ready solution announced to be coming soon.