Open Source AI Models 395

Open-source ChatGPT UI clone for OpenAI's chat models. Chatbot UI is an advanced chatbot kit for OpenAI's chat models aiming to mimic ChatGPT's interface and functionality. It is an open-source clone of OpenAI's ChatGPT UI that allows users to plug in their API key to use the UI with the OpenAI API. Chatbot UI is 100% unaffiliated with OpenAI and only communicates with their API.

AI assistant for financial research, providing access to company data and insights. AlphaWatch is an AI assistant used by hedge funds for financial research, now accessible to everyone. It provides access to over 3,000 companies' filings, transcripts, research, and news. AlphaWatch offers AI agents that help solve critical operational issues by analyzing complex enterprise data. It is designed for deep research, expanding accessibility with multilingual models, and automating tasks safely with human oversight.

Open-source no-code platform for creating, managing, and deploying advanced data and A.I workflows. Domino is an open-source no-code platform for creating, managing, collaborating and deploying advanced data and A.I workflows. Domino closes the gap between ideas and their implementation allowing everyone to build advanced data and A.I workflows with ease. It provides an intuitive Graphical User Interface that facilitates creating, editing and monitoring any type of workflow, including integrations with Advanced Data Processing Tools, Machine Learning & Generative AI algorithms, External APIs and Social Media.

Decentralized AI ecosystem for local or P2P model execution with privacy. LLMule is a decentralized AI ecosystem that allows users to run models locally or connect to a P2P network. It emphasizes data privacy, community-shared models, and the ability to share compute power. LLMule aims to provide AI freedom outside of big tech control by democratizing access to artificial intelligence through distributed computing.

Desktop app securing AI apps from attacks by monitoring MCP communications. MCP Defender is a desktop application designed to automatically secure AI apps like Cursor, Claude, Visual Studio Code, and Windsurf from various attacks. It functions as an AI Firewall, monitoring and protecting Model Context Protocol (MCP) communications by intercepting tool calls and responses. It verifies these against security signatures and alerts the user if it detects any malicious activity, allowing them to block or allow the action. It provides intelligent LLM-powered threat detection and acts as a secure proxy, analyzing communications in real-time.

Open-weight rectified flow Transformer for image generation and editing. FLUX 2 Dev (FLUX.2-dev) is a frontier-level, open-weight rectified flow Transformer for image generation and editing, developed by Black Forest Labs. It integrates a 32B rectified flow core, a long-context vision–language model (VLM), and multi-reference editing capabilities to produce production-grade visuals. It is designed for various applications including high-fidelity animal renders, ad creatives, hero banners, 3D concept art, product renders, interactive filters, and avatars.

Private, local AI assistant for secure AI conversations using open-source models. Sanctum is a private, local AI assistant that allows users to experience secure AI conversations powered by open-source models encrypted locally on their device. It enables users to run full-featured LLMs in seconds, ensuring data privacy and security.

Klee is a local and secure AI-powered note and knowledge base application. Klee is a note and knowledge base application with client-side AI models, offering local and secure AI on your desktop. It supports DeepSeek, Llama, Qwen, and Gemma, ensuring data security and privacy with on-device processing.

PyTorch library for model interpretability across modalities. Captum is a PyTorch library for model interpretability. It provides tools and techniques to understand and attribute the predictions of PyTorch models across various modalities, including vision and text. Captum supports most PyTorch models and allows for easy implementation and benchmarking of new interpretability algorithms.

Open-source platform for generating videos from text using OpenAI's Sora model. SoraWeb is an open-source platform that simplifies video creation by allowing users to generate videos online with OpenAI's Sora model using text. It offers instant video generation and personalized editing experiences through advanced sora technology, featuring easy one-click website deployment.

No-code platform to create, manage, and optimize custom AI models for businesses. Entry Point is a no-code platform that helps you create custom AI models for your business or projects. Manage training data, generate synthetic examples, estimate fine-tuning costs, and optimize models — all in one place! Train, manage, and evaluate custom large language models (LLMs) fast and efficiently on Entry Point AI with no code required.

Multimodal AI platform for image, video, and audio generation Flux 3 is Black Forest Labs' multimodal AI platform for generating and editing images, videos, and audio. It uses a unified Self-Flow architecture to support creative workflows, native audio generation, reference-based editing, and action prediction for real-world visual intelligence.

Open-source tool enabling language models to run code on your computer. Open Interpreter is an open-source project that lets language models like Code-Llama run code on your computer to complete tasks. It provides a ChatGPT-like interface in your terminal, allowing you to summarize PDFs, visualize datasets, and control your browser.

Open-source AI cost management platform for SaaS businesses using LLMs. Fiorino.AI is an open-source platform designed to track and optimize AI costs, particularly for SaaS businesses using Large Language Models (LLMs). It provides granular LLM usage metrics, custom pricing options, and usage-based billing capabilities. The platform is built for scale, prioritizes privacy, and integrates with any LLM provider, giving users control over their AI spending.

Software studio creating functional apps for macOS, iOS, and visionOS. App ahead is a software studio led by Martin Lexow, crafting opinionated apps that are honest and functional for macOS, iOS, and visionOS. It offers a range of apps including PolyCapture, Cursor Pro, Keystroke Pro, Mirror Magnet, AI Transcription, 3D Scan Pro, and Codepoint.

Open-weights uncensored AI video generator based on LTX 2.3 for local GPU use. Sulphur 2 is an uncensored, open-weights AI video generator fine-tuned on Lightricks LTX 2.3. It is a community-released model designed to run locally on consumer GPUs. The release includes base weights, distilled LoRAs for faster generation, and specialized ComfyUI workflows. It focuses on high-fidelity realism by training on approximately 125,000 video clips while intentionally excluding 2D animation. As a derivative of the LTX 2.3 DiT-based foundation model, it supports both text-to-video and image-to-video tasks and includes a local prompt enhancer based on Qwen 3.5 to maintain a fully on-device creative pipeline.

Open-source web platform for generating videos from text using OpenAI's Sora model. SoraWebui is an open-source web platform that enables users to generate videos from text using OpenAI's Sora model. It simplifies the video creation process, allowing for easy deployment and use. With SoraWebui, anyone can create videos by simply inputting text, making it an accessible tool for both professionals and enthusiasts in video production and AI technology.

AI-native API gateway for AI Agent development and LLM API management. Higress is an AI native API gateway based on Istio and Envoy, which can be extended with Wasm plugins written in Go/Rust/JS. It offers AI Gateway, MCP Server Hosting, Kubernetes ingress controller, Microservice gateway and Security gateway. Higress AI网关提供多模型灵活切换与兜底重试、大模型内容安全与合规、语义化缓存、多 API Key 均衡、Token 配额管理和限流、大模型流量灰度、调用成本审计等能力，帮助企业开发 Agent、管理LLM API.

Privacy-focused AI service with end-to-end encryption for secure data processing. Privatemode AI is an AI service that prioritizes data privacy and security. It encrypts data end-to-end using confidential computing, ensuring that your information remains secure during AI processing. It offers both a chat application and an inference API, catering to individuals and developers who need to use AI with sensitive data.

Open-source AI-powered rich text editor with Markdown support and private deployment. AiEditor is an open-source, AI-powered rich text editor that is out-of-the-box, fully framework supported, and Markdown friendly. It supports private deployment and private LLMs API key. It's a next-generation rich text editor for AI.

Open-source AI video model for cinematic text-to-video and image-to-video generation. Happy Horse is an open-source AI video model and generator designed for high-quality text-to-video and image-to-video creation. It features Happy Horse 1.0, which offers joint audio-video generation, multilingual lip-sync, and fast 1080p output. Built for creative teams, it focuses on production-ready motion and cinematic quality, allowing users to transform text prompts or static images into dynamic clips with synchronized audio. The platform is positioned as a practical tool for concept validation, storyboard rough cuts, and social media testing, emphasizing open-source access and benchmark-driven performance.

Open-source .NET Core framework for building universal bots with AI and database integration. Botticelli is an open-source .NET Core framework for building universal bots integrated with databases, queue brokers, speech engines, and AI engines (such as Gpt-j and ChatGPT). It supports cross-platform development, is reliable, easy to use, and easy to deploy with Docker support. It also facilitates integration with databases, AI solutions (Botticelli.AI), speech synthesizers (Botticelli.Talks), queue brokers (Botticelli.Bus), and scheduling (Botticelli.Scheduler).

Open-source AI model to convert PDFs into customizable audio outputs. PDF2Audio is an open-source AI model that transforms PDFs into flexible and customizable audio outputs. It allows users to create podcasts, lectures, and summaries from PDF documents. The tool uses OpenAI GPT models for text generation and text-to-speech conversion, offering features like multiple PDF uploads, customizable instruction templates, model customization, different speaker voices, and introductory instructions.

Open-source AI image generator for high-quality, bilingual, photorealistic images. Z-Image is a groundbreaking open-source AI image generation model that challenges the assumption that bigger is always better. It achieves photorealistic quality and superior bilingual text rendering (English and Chinese) with a highly efficient 6 billion parameter model, optimized for consumer GPUs (16GB VRAM). Z-Image offers a versatile model family, including Z-Image-Turbo for speed and Z-Image-Edit for precise modifications, making high-end AI art accessible to everyone.