Open Source AI Models 395

AI assistant for generating shell commands from natural language. BashBuddy is an AI assistant that helps you generate bash (or powershell) commands with natural language. It can be used completely locally, or through BashBuddy Cloud for faster command generation. It understands context, integrates with git, and will soon have project awareness. It supports multiple platforms including macOS, Linux, Windows, Bash, Zsh, and PowerShell.

Infinite memory. Persistent identity. Evolving intelligence. EverMemOS, powered by EverMind, is entering beta on the new cloud platform. The Memory Genesis Competition 2026 officially launches alongside it. EverMemOS, powered by EverMind, is entering beta on the new cloud platform. The Memory Genesis Competition 2026 officially launches alongside it.

Visual generative AI platform for automating and scaling video and image creation with licensed data. BRIA.ai is a visual generative AI platform that allows users to automate and scale the creation of video and images. It offers fully-licensed datasets, source-available models, and APIs to create tailored generative AI solutions for enterprise solutions. Bria AI's platform gives you the building blocks to create powerful, commercially-ready generative AI solutions tailored to the needs of your enterprise.

Low-cost, scalable inference for high-volume AI workloads Doubleword is an AI inference platform for high-volume workloads, offering OpenAI-compatible access to open-weight language, vision, OCR, and embedding models. It supports real-time, async, and approximately 24-hour batch inference, allowing users to trade latency for substantially lower token costs. Doubleword is designed for agentic reasoning, evaluations, synthetic data generation, annotation, extraction, coding workflows, and large-scale data processing. Its inference stack includes optimization technologies such as FlashOffload, Speculative KV Coding, and Cloudburst to improve throughput, cache efficiency, and startup times.

Automated open-source AI model optimization and deployment API platform. RunInfra is an AI inference optimization and deployment platform that builds production-ready APIs from plain language descriptions of open-source models or full apps. Backed by Y Combinator, it benchmarks various serving engines (like vLLM, SGLang, and TensorRT-LLM) across different NVIDIA GPUs to find the most cost-effective and low-latency configuration. It leverages its automated Forge agent to optimize kernels, quantize models (AWQ, GPTQ, FP8), and handle continuous batching and KV cache tuning. Users can deploy on RunInfra's managed infrastructure with scale-to-zero capabilities or export the fully runnable deployment kit (Dockerfile, configs) to host on their own infrastructure like RunPod, Modal, or local hardware.

AI image generator for accurate text rendering and advanced editing. Qwen Image AI is an open-source image generation and editing foundation model from Alibaba’s Qwen team. It is a groundbreaking 20B Multi-Modal Diffusion Transformer (MMDiT) model designed for accurate text-in-image rendering and advanced edits like object insertion/removal and style transfer. It revolutionizes text-to-image generation with exceptional text rendering capabilities, being the first model to successfully handle complex multi-line text layouts and paragraph-level content in both English and Chinese. Built on advanced diffusion technology, Qwen Image AI delivers state-of-the-art performance, excelling in text rendering accuracy and generating diverse visuals from photorealistic images to stylized artwork with perfect text fidelity. It aims to lower technical barriers in visual content creation, empowering designers, marketers, and content creators to produce professional-grade visuals with precise text integration through simple prompts.

Flux AI is an AI image generator by Black Forest Labs, offering high-quality visuals. Flux IMAGE GENERATORS, developed by Black Forest Labs, features FLUX Pro, FLUX Dev, and FLUX Schnell. These advanced models create stunning photorealistic visuals, artistic masterpieces, and innovative designs. Experience cutting-edge AI image generation with Flux AI, offering unmatched speed and quality beyond Stable Diffusion 3.

Open-source framework for automating development workflows with custom AI workflows. Patched is an open-source framework designed to automate IT and development workflows. It allows development teams to create custom AI workflows (patchflows) to automate tasks such as code reviews, documentation, and patching. These workflows can be self-hosted and integrated with preferred LLMs, ensuring privacy and control. Patched aims to reduce costs and improve SLAs by using agentic workflows to fix bugs, patch vulnerabilities, update documentation, and troubleshoot system issues.

GenAI-powered API testing tool automating test generation and streamlining workflows. FlowTestAI simplifies end-to-end API testing by automating test generation from OpenAPI specifications using natural language and LLMs. It provides an IDE, CLI, and analytics to streamline workflows for developers and QA teams. FlowTestAI is a low/no-code tool powered by Generative AI, designed to craft, visualize, and manage API-first workflows with speed, lightweight architecture, and localized operation, ensuring privacy.

Open-source tool for automated head-to-head evaluation of GenAI systems using LLM judges. AutoArena is an open-source tool designed to automate head-to-head evaluations of GenAI systems using LLM judges. It allows users to quickly and accurately generate leaderboards comparing different LLMs, RAG setups, or prompt variations. Users can fine-tune custom judges to fit their specific needs. AutoArena facilitates trustworthy evaluation of LLMs, RAG systems, and generative AI applications through automated head-to-head judgement.

Open-source local AI employee office with a shared autonomous knowledge base. WUPHF is an open-source, collaborative office of AI employees that run locally on your machine. It features a team of specialized agents—including a CEO, Engineer, Designer, CMO, and PM—who share a 'brain' or knowledge base to maintain context across tasks. Unlike simple prompt chains, these agents interact autonomously in shared channels, manage dependencies, and use local tools (like GitHub CLI and filesystem ops) to execute complex goals such as shipping code, creating assets, and writing documentation without constant human intervention.

Open-source GenAI/LLM observability platform with APM, native to OpenTelemetry. OpenLIT is an open-source GenAI and LLM observability platform native to OpenTelemetry. It provides Application Performance Monitoring (APM) & Observability for GenAI and LLM applications, unifying traces and metrics in a single interface. OpenLIT simplifies AI development workflows, especially for Generative AI and LLMs, by streamlining tasks like experimenting with LLMs, organizing prompts, and securely handling API keys.

AI content creation platform with templates, AI bots, and image generation. ClarityWrite is an AI-driven content creation platform designed for marketers, entrepreneurs, and creators. It offers tools to generate high-quality written, visual, and code content using built-in templates, AI bots, and image generation. The platform aims to eliminate writer's block and provide limitless content creation possibilities through an open-source SaaS script powered by OpenAI APIs.

Lightweight open language models by Google, based on Gemini technology. Google’s Gemma is a family of lightweight, state-of-the-art open language models (LLMs) developed using the same research and technology as Google's Gemini models. It includes 2B and 7B parameter versions, with both base and instruction-tuned modifications. Gemma is designed with AI principles to ensure safe and reliable use, featuring cross-device compatibility and optimization for Google Cloud and NVIDIA GPUs. It is accessible for free on platforms like Kaggle and Colab, and through Google Cloud with Vertex AI or GKE.

A community and platform for Llama models, technology, and enthusiasts. Llama Family is a community and platform dedicated to Llama models, technology, and enthusiasts. It aims to foster the development of general artificial intelligence through open source initiatives. The platform provides resources such as models, computing power, projects, and educational materials. It welcomes developers and technology enthusiasts to join the Llama Chinese community and contribute to the open-source Llama ecosystem, covering areas from large to small models, text to multi-modal applications, and software to hardware algorithm optimization.

A basic online chat platform for user interaction. AI Chatroom is an online chat platform where users can interact with each other. It appears to be a simple chatroom with basic functionalities, potentially built using open-source code like the 'bulita' project mentioned in the content. Users can post messages, and the administrator (referred to as '群主' or group owner) has the ability to manage the chatroom.

LLM Labs helps developers compare language models side-by-side for informed decisions. LLM Labs enables indie developers to test and compare the latest open-source and proprietary language models simultaneously in a side-by-side interface. Get visual comparisons of performance, speed, and usability to make informed decisions for your projects.

Open-source web app for interacting with LLMs, fine-tuning results, and saving prompts. Prompto is an open-source web application designed to make interacting with Large Language Models (LLMs) simple and efficient. It allows users to fine-tune results, chat or query, and save prompts. Prompto runs entirely in your browser as a Progressive Web Application (PWA) and communicates directly with your chosen LLM provider through LangChain.js integrations.

Open-source AI agents to automate outbound sales and scale sales organizations. QRev Dynamic Salesforce 2.0 is an open-source AI agent platform designed to scale outbound sales organizations. It leverages AI agents to automate tasks such as prospect research, outreach, competitive research, and email responses, aiming to significantly reduce the cost and time associated with traditional sales processes.

Local AI solution for Mac and Windows with focus on accessibility and privacy. HyperMink AI is a local AI solution for Mac and Windows that offers fast, local, long-form conversations, local PDF and CSV inference, vision capabilities, and the ability to read web pages. It requires no complex installations, subscriptions, or GPU. HyperMink System 1 is a personal AI assistant accessible via a simple USB plug-in. The platform emphasizes accessibility and privacy, aiming to demystify AI for everyday users.

AI system source code solutions provider with PHP and Java versions. 码多多技术社区 is a technology team specializing in providing AI system source code solutions. They offer open-source projects like "ChatMoney-Super All-in-One AI Monetization System", "ChatAI-Chat Painting System", and "ChatPaper-Paper Writing System", available in both PHP and Java. They provide AI solutions for various industries, including AI-powered office software, social entertainment, marketing, and traditional industries.

Open-source AI model based on Llama 70B, surpassing GPT-4 with self-correction. Reflection 70B is an advanced open-source AI language model built on the Llama 70B architecture. It distinguishes itself by surpassing GPT-4 through innovative self-correction techniques. It excels in handling complex tasks with high accuracy and supports a wide range of applications. It is designed to engage in human-like conversation, assist with various tasks, and provide information across a wide range of topics.

AI-powered visual creation platform for generating India-specific images in Hindi and English. BharatDiffusion.ai is an AI-powered visual creation platform tailored for India's diverse audience. It enables brands, eCommerce businesses, and creators to generate region-specific visuals in Hindi and English. The platform uses an AI-powered Image Generation model fine-tuned to vividly portray India’s diverse landscapes, culture, and heritage. BharatDiffusion aims to be open-source, empowering the community to create stunning, high-quality images that capture the essence of India.

Free, open-source resume builder with job tracking and mock interview features. Reactive Resume is a free and open-source resume builder that simplifies the process of creating, updating, and sharing your resume. It includes a custom-built Job Tracker and Mock Tests to help users build Job Description Specific Resumes with Keyword Matching. Flow Jobs is presented as a complete job tracking solution to simplify the job hunt, allowing users to track applications, build standout resumes, and craft impressive CVs. It also offers AI-powered mock interviews.