Open Source AI Models 175

Open-source, offline ChatGPT alternative prioritizing privacy and customization. Jan is an open-source ChatGPT alternative that runs 100% offline on your computer. It utilizes open-source AI models, prioritizes privacy, and is highly customizable. Jan is available for Windows, Mac, and Linux, with a mobile version coming soon. It provides an OpenAI-equivalent API server and allows for local server and API usage.

Open-source AI platform with customizable AI tools and models. MimicPC is an open-source AI platform that provides customizable and affordable access to various AI tools and models. It allows users to create AI images, videos, and audio, train LoRA models without deployment, and add custom models for endless possibilities. It offers pre-installed AI apps, customizable options, and workflow templates, making it suitable for both beginners and experts.

Serverless decentralized AI compute for deploying and scaling models Chutes is a decentralized serverless AI compute platform for deploying, running, and scaling open-source AI models through a web platform or API. It supports production inference, private confidential GPU workloads, and multiple modalities including image, video, speech, and music.

Managed cloud hosting for OpenClaw, offering one-click deployment of a 24/7 private AI assistant. MyClaw.ai is a managed cloud hosting platform designed specifically for OpenClaw (formerly known as Clawdbot and Moltbot). It allows users to deploy their own dedicated, always-on AI assistant in one click without any technical setup or DevOps knowledge. The platform handles server maintenance, environment configuration, security updates, and daily backups, providing a private, isolated container for each user. OpenClaw itself is an open-source AI assistant capable of performing tasks like managing emails, reviewing code, controlling browsers, and integrating with third-party apps like Slack and GitHub.

Unified model for segmenting objects across images and videos with high precision. Meta Segment Anything Model 2 (SAM 2) is the first unified model for segmenting objects across images and videos. It allows users to select objects in any image or video frame using a click, box, or mask as input. SAM 2 is designed for fast, precise object selection and offers state-of-the-art performance for object segmentation in both images and videos. The models are open source under an Apache 2.0 license.

Open-source fine-tuning & reinforcement learning for LLMs. 🦥 Unsloth makes it super easy for you to train text-to-speech (TTS), diffusion, multimodal/image and text models like Llama 3 100% locally or for free on platforms such as Google Colab and Kaggle. We streamline the entire training workflow, including model loading, quantizing, training, evaluating, running, saving, exporting, and integrations with inference engines like Ollama, llama.cpp, and vLLM.

Open-source NVR with local AI object detection for IP cameras. Frigate NVR is an open-source Network Video Recorder (NVR) designed for IP cameras, featuring real-time local object detection. It processes video feeds locally using AI, ensuring that camera footage never leaves the user's home. Frigate leverages the Google Coral TPU to perform advanced analysis, identifying objects of interest such as people, cars, and other objects, thereby reducing false positives. It integrates with home automation platforms like Home Assistant, OpenHab, and NodeRed via MQTT, providing low-latency camera entities and real-time sensors for automation and notifications.

A framework for building knowledge assistants with LLMs connected to enterprise data. LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data. It offers document parsing, data extraction, knowledge management, and an agent framework to build production agents that can find information, synthesize insights, generate reports, and take actions over the most complex enterprise data.

Open-source AI agent for automating browser-based workflows using LLMs and Computer Vision. Skyvern is an open-source AI Agent that helps companies automate browser-based workflows. It replaces brittle scripts with a simple API endpoint to automate tasks on hundreds of different websites using LLMs and Computer Vision. Skyvern fully automates manual workflows and offers features like CAPTCHA support, two-factor authentication handling, proxy network support, and explainable AI.

Open-source AI code assistant for customizable autocomplete and chat experiences in IDEs. Continue is an open-source autopilot for software development built to be deeply customizable and continuously learn from development data. It's a VS Code extension that brings the power of ChatGPT to your IDE. You can connect any models and any context to build custom autocomplete and chat experiences inside the IDE.

AI-powered email management tool for automation, unsubscribing, blocking, and analytics. Inbox Zero is an open-source email application that uses AI to automate email management, bulk unsubscribe from newsletters, block cold emails, and provide email analytics. It helps users achieve 'inbox zero' by intelligently automating responses, organizing inboxes, and cutting email time in half. Approved by Google and CASA Tier 2 approved, it prioritizes user privacy and data security.

AI community platform for open-source ML models, datasets, and applications. Hugging Face is an AI community building the future through open source and open science. It provides a platform where the machine learning community collaborates on models, datasets, and applications. Hugging Face offers tools for creating, discovering, and collaborating on ML projects, including hosting unlimited models, datasets, and applications. It also provides paid Compute and Enterprise solutions to accelerate ML development.

Open-source AI model community and one-stop model service platform. ModelScope is an open-source AI model community and innovation platform founded in June 2022 by Alibaba's Tongyi Lab and the CCF Open Source Development Committee. It provides one-stop services for model exploration, inference, training, deployment, and application building, while also supporting a rich open-source ecosystem, datasets, studios, and model development tools.

Tencent AI model for multimodal Q&A and content retrieval Tencent Hunyuan Large Model is a self-developed Tencent AI model with strong text and multimodal capabilities. Its Hunyuan API integrates Tencent's content ecosystem, including WeChat official accounts and video accounts, to provide up-to-date, in-depth content retrieval and AI Q&A. The platform is designed to help users efficiently obtain information, knowledge, and inspiration, and it is positioned for use across multiple business scenarios to improve value and efficiency.

Model-sharing hub for AI art generation, specializing in Stable Diffusion. Civitai is a model-sharing hub for the AI art generation community, focusing on Stable Diffusion models, embeddings, and LoRAs. It provides a platform for creators to share their models and for users to browse, review, and download them. The site also features images shared by the community, along with prompts to help users get started with AI art generation.

Open-source LLMOps platform for building and operating generative AI applications. Dify.AI is an open-source LLMOps platform designed to help developers build and operate generative AI applications. It offers visual management of prompts, operations, and datasets, enabling the creation of AI apps in minutes or the integration of LLMs into existing applications for continuous improvement. Dify supports the creation of Assistants API and GPTs based on any LLMs and provides features like RAG engine, orchestration studio, prompt IDE, enterprise LLMOps, BaaS solution, LLM agents, and workflows.

Open-source platform providing easy-to-use AI text and image generation APIs. Pollinations.AI aims to diversify creativity by providing an open-source platform with easy-to-use text and image generation APIs. It allows users to imagine new worlds with AI, offering customized outcomes and specific aesthetics for companies. The API integrates AI creation directly into websites and social media platforms, making creation easy, fast, and fun.

A platform for deploying and running machine learning models with a simple API and pay-per-use pricing. Deep Infra offers cost-effective, scalable, easy-to-deploy, and production-ready machine-learning models and infrastructures for deep-learning models. It provides a platform to run top AI models using a simple API, with pay-per-use pricing and low-latency inference. Users can deploy custom LLMs on dedicated GPUs and access various models for text generation, text-to-speech, text-to-image, and automatic speech recognition.

Ultralytics provides vision AI tools and platforms for creating, training, and deploying ML models. Ultralytics is a company focused on empowering individuals and businesses by providing vision AI tools. Their flagship product, Ultralytics HUB, is an AI platform designed for creating, training, and deploying machine learning models with a no-code interface. They also offer Ultralytics YOLO, a state-of-the-art AI tool for image classification, object detection, and instance segmentation. Ultralytics aims to simplify the process of building and deploying AI models, making it accessible to users regardless of their field of work.

AI Acceleration Cloud for fast inference, fine-tuning, and training. Together AI is an AI Acceleration Cloud providing an end-to-end platform for the full generative AI lifecycle. It offers fast inference, fine-tuning, and training capabilities for generative AI models using easy-to-use APIs and highly scalable infrastructure. Users can run and fine-tune open-source models, train and deploy models at scale on their AI Acceleration Cloud and scalable GPU clusters, and optimize performance and cost. The platform supports over 200 generative AI models across various modalities like chat, images, code, and more, with OpenAI-compatible APIs.

Cloud platform for building, tuning, and running AI models on NVIDIA GPUs. Nebius is a cloud platform designed for AI explorers, offering efficient tools to build, tune, and run AI models and applications on NVIDIA GPUs. It provides a flexible architecture, tested performance, and long-term value by optimizing every layer of the stack. Nebius also features AI Studio, a comprehensive platform for fine-tuning AI models at scale, and the AI Discovery Award for startups in drug discovery and healthtech.

A computer vision platform for building and deploying models with automated tools. Roboflow is a computer vision platform designed for developers and enterprises. It provides tools to build and deploy computer vision models, including automated annotation, model training infrastructure, and deployment solutions. The platform supports various industries and use cases, offering features like data curation, collaborative labeling, model evaluation, and edge deployment. Roboflow aims to accelerate computer vision roadmaps with best-in-class tooling and expert guidance.

Cloud API to run, fine-tune, and deploy open-source machine learning models. Replicate is a cloud API platform that allows users to run open-source machine learning models. It enables users to run and fine-tune models, and deploy custom models at scale with a single line of code. Replicate hosts thousands of models contributed by the community, offering production-ready APIs for various AI tasks such as image generation, video generation, image restoration, captioning, speech generation, music generation, and text generation.

An open-source autonomous agent framework that grows, learns, and automates tasks across multiple platforms. Hermes Agent is an open-source, autonomous AI agent framework developed by Nous Research. Unlike standard chatbots or coding assistants, it is designed to live on a user's server, maintain persistent memory, and develop new skills over time. It can be integrated across various communication platforms like Telegram, Discord, and Slack, and it features robust sandboxing capabilities using Docker or SSH. It is capable of executing Python scripts, automating web browsing, and delegating tasks to subagents to handle complex, multi-step pipelines.