Open Source AI Models 395

Stablecog is a free and open-source AI image generator using Stable Diffusion and Kandinsky. Stablecog is a simple, free & open source tool for creating AI-generated images. It uses Stable Diffusion and Kandinsky. You can use the default server for free without a sign-up, install, or predetermined limits. You can also connect to your own server. Stablecog also offers paid plans for users who need more resources.

PandasAI integrates AI into pandas, enabling conversational data analysis with natural language queries. PandasAI is a Python library that integrates generative artificial intelligence capabilities into pandas, making dataframes conversational. It allows users to ask questions to their enterprise data in natural language and get real-time data insights. It integrates with data infrastructure, easily connecting to data sources like SQL, NoSQL, CSV, and xls. PandasAI enhances analytics with actionable insights, detailed reports, and visual data representation. It is an open-source library aimed at democratizing data analysis for better data-informed decision-making.

Anyscale is an AI application platform for building, running, and scaling AI applications. Anyscale is the leading AI application platform that allows developers to build, run, and scale AI applications instantly. It leverages Ray, a distributed computing framework, to optimize performance and lower costs for AI workloads. Anyscale offers tools for compute governance, developer tooling, and supports any cloud, accelerator, and stack.

Open-source library for building fast, model-agnostic AI agents with memory and tools. Agno is a lightweight, open-source library to build lightning-fast, model-agnostic multimodal AI agents. It allows users to add memory, knowledge, tools & reasoning to their agents. It's an open-source platform to build, ship and monitor agentic systems, designed to be model agnostic, blazing fast, and future-proof.

Open-source AI generator creating 1080p video and synchronized audio in one pass. HappyHorse is an advanced, open-source AI video generator that jointly synthesizes high-quality 1080p video and synchronized audio in a single pass. Utilizing a 40-layer Transformer architecture, it integrates text, video, and audio tokens simultaneously, eliminating the need for post-processing audio. It supports both text-to-video and image-to-video workflows and features a native 7-language lip-sync capability. The model is highly efficient, using DMD-2 distillation to achieve high-quality results in just 8 inference steps, making it accessible for single-GPU deployment. It is ranked #1 on the Artificial Analysis Arena for its performance and prompt adherence.

MultiChat AI: Chat with multiple LLMs, generate images, and access pre-built assistants. MultiChat AI is a platform that allows users to chat with multiple open-source LLMs (Large Language Models) like Mixtral, Llama-3, Claude-3, Gemini 1.5 Pro, Perplexity, and GPT-5 all in one place. It offers access to premium models, image generation and editing tools, web search, and file uploads. MultiChat AI also provides pre-built assistants designed using crafted prompts and suitable LLMs, including NSFW AI chat capabilities.

AI platform transforming 2D images into accurate, fully-textured 3D models. SAM 3D is an AI-powered 3D reconstruction platform that transforms single 2D photographs into accurate, fully-textured 3D models in seconds. It provides professional-grade 3D modeling capabilities to developers, designers, researchers, and content creators worldwide, democratizing access to enterprise-level 3D reconstruction without expensive equipment or technical expertise. It eliminates traditional 3D modeling barriers by offering a single-image workflow, unlike methodologies that demand multiple photographs or specialized hardware.

Open-source visual language model for understanding images with text prompts. Moondream is an open-source visual language model (VLM) designed to understand images using simple text prompts. It is lightweight, fast, and capable, requiring only 1GB of space. Moondream can be used for various applications, including image captioning, object detection, visual question answering, and more. It's designed for developers who want a versatile and easy-to-use visual AI solution.

OmniGen AI is a free online AI text-to-image generator with editing capabilities. OmniGen is an advanced text-to-image AI model that combines text-based image creation, editing, and visual-conditional generation in a unified framework. OmniGen seamlessly transforms prompts into high-quality, visually rich outputs with no extra tools needed. It is a free online text to image generator, enabling users to create consistent images with simple prompts.

Web-based platform for code hosting, version control, and collaboration. GitHub is a web-based platform for version control and collaboration. It is primarily used for code hosting, allowing developers to track and manage changes to their code. GitHub facilitates collaboration among developers, enabling them to work together on projects, review each other's code, and contribute to open-source projects. It provides tools for issue tracking, project management, and team communication, making it a comprehensive platform for software development.

Open-source platform for AI-driven market analysis in emerging markets. theMOG (The Mirror of Galadriel) is an open-source platform that revolutionizes market analysis for businesses in emerging markets. It provides AI-driven insights and customizable dashboards, integrating real-time data and leveraging machine learning to uncover hidden patterns and predict market trends. The platform aims to democratize market analysis and empower businesses to make smarter, data-driven decisions, particularly in the commodity sectors in MENA, Africa, and Asia.

AI-powered Markdown editor for efficient and standardized document creation. MarkDX is an open-source AI Markdown editor designed to help users write Markdown documents more efficiently. It leverages AI to ensure Markdown documents adhere to standards, offering a smooth, simple, and powerful editing experience. MarkDX supports Markdown and MDX formats, providing features like preview, AI suggestions, code generation, translation, and real-time collaboration.

AI platform to generate Studio Ghibli-style artwork from photos. Ghibli AI is a revolutionary platform that uses artificial intelligence to generate stunning artwork in the style of Studio Ghibli animations. Transform your photos into magical Ghibli-style art with our free AI image generator. It offers features like a free generator, ChatGPT integration, style transfer, and high-resolution image generation.

Web crawler for LLM/RAG, reduces retrieval time. HyperCrawl is a zero-latency web crawler specifically designed for retrieval-based LLM development and RAG applications. It aims to significantly reduce retrieval time in RAG systems by up to 95%. It's built for ML engineers to boost retrieval processes by eliminating the crawl time of domains, using advanced methods to create a novel, ML-first web crawler.

HyperLLM offers tools for training, tuning, and deploying efficient language models and retrieval-based AI applications. HyperHRT introduces a new generation of language model architecture developed at the Indian Institute of Technology, Patna that you can train & tune and integrate with a small-language model. HyperHRT works on real-time decentralised fine-tuning approach. HyperCrawl is a part of HyperLLM where they are dedicated to build the infrastructure for a world of future LLMs. Models that requires less computational resources & outperforms any models available. Exthalpy is serverless retrieval to power the future of AI. Build retrieval-first AI applications and models that are less dependent on computation-heavy training processes.

Rompt.ai helps fine-tune AI products through A/B testing of prompts. Rompt helps developers and companies fine-tune their AI-powered products by making it possible to run extensive A/B testing experiments on their prompts. It allows users to generate massive A/B tests from their prompts by leveraging open-source infrastructure to generate and evaluate prompt variations, uncovering high-performing prompts with an unbiased rating experience.

Open-source project for creating animated videos from a single image and motion video. Magic Animate is a groundbreaking open-source project that simplifies animation creation, allowing you to produce animated videos from a single image and motion video. This website is designed to aggregate relevant content for easy learning and practical use. It's a diffusion-based framework for human image animation, excelling in maintaining temporal consistency, faithfully preserving the reference image, and significantly enhancing animation fidelity. It can animate reference images with motion sequences from various sources, including cross-ID animations and unseen domains like oil paintings and movie characters. It also integrates seamlessly with T2I diffusion models like DALLE3, bringing text-prompted images to life with dynamic actions.

AI toolkit for web apps, simplifying form-filling with voice and text input. Form2Agent AI is an AI-powered toolkit designed to simplify the integration of advanced AI features into web applications. It offers seamless integration, hands-free operation, multi-language support, and AI-assisted data entry. It is adaptable to various industries and streamlines form-filling processes by providing voice-assisted AI solutions that improve user experience and guarantee precise data entry and content manipulation with text, voice, and file input support.

NVIDIA's open-source enterprise AI platform for secure, private, and scalable task automation. NemoClaw is an open-source enterprise AI agent platform developed by NVIDIA, designed for secure deployment, privacy protection, and scalable task automation. It is deeply integrated with the NVIDIA NeMo framework and NIM (NVIDIA Inference Microservices) to help businesses achieve high-efficiency task automation and intelligent decision-making. Unlike consumer-level AI assistants, NemoClaw focuses on data governance, regulatory compliance, and large-scale operations, providing a hardware-agnostic architecture that works with NVIDIA, AMD, and Intel hardware.

Harmonai is an open-source generative audio tool for accessible music production. Harmonai is a community-driven organization and a Stability AI Lab focused on releasing open-source generative audio tools. The goal is to make music production more accessible and fun for everyone. They aim to empower artists by providing tools to express their creativity without limitations and generate custom, infinite sound libraries.

Predibase is a low-code AI platform for building, fine-tuning, and deploying state-of-the-art AI models, including LLMs. Predibase is a low-code AI platform that enables engineers and data scientists to build, optimize, and deploy state-of-the-art models, ranging from linear regressions to large language models, using minimal code. It specializes in fine-tuning and serving LLMs, allowing users to customize and serve open-source models that can outperform GPT-4 within their own cloud or Predibase's infrastructure. The platform offers features like reinforcement fine-tuning, multi-LoRA inference, and autoscaling infrastructure to ensure unmatched accuracy and speed in training and serving AI models.

Opensource AI pair programmer for code editing and AI-assisted development. PapertLab is an opensource AI pair programmer that seamlessly collaborates with Large Language Models to edit code in your local Git repository or any other codebases. It offers AI-assisted development through features like real-time code suggestions, refactoring assistance, and automated code generation.

Free, privacy-focused tool to remove image backgrounds directly in your browser. ByeBackground is a free, privacy-focused, browser-based tool that removes image backgrounds effortlessly with a single click. It operates directly in your browser without sending data to remote servers, ensuring 100% privacy. There are no ads or trackers. It respects the original image resolution and uses cutting-edge technologies for efficient background removal. ByeBackground aims to be an economical and ethical solution, not relying on big servers or external services.

Open-source AI DevOps agent for securing, deploying, and maintaining infrastructure. Stakpak is an open-source AI DevOps agent written in Rust, designed to help users secure, deploy, and maintain production-ready infrastructure directly from their terminal. It provides capabilities for incident handling, cloud cost analysis, IAM security, and application containerization, aiming to simplify and automate complex DevOps workflows.