Open Source 129

GPTBots.ai: The Ultimate AI Agent Development Platform. Build, customize, and deploy intelligent agents tailored to your business needs. Simplify workflows, enhance customer experiences, and unlock new growth opportunities with ease. GPTBots.aiis an enterprise-grade no-code AI Agent development and management platform that integrates cutting-edge Multi-Agent technology, enabling businesses to flexibly build, customize, and deploy intelligent agent teams. Through modular architecture and pre-configured AI Agents, the platform simplifies workflows, enhances customer experiences, and provides efficient, stable AI solutions that drive business growth and improve efficiency. GPTBots.aisupports end-to-end services from AI solution design and deployment to operations, featuring visual operation capabilities and a rich ecosystem of intelligent agents. It is applicable to various enterprise business scenarios, empowering enterprises to achieve intelligent transformation.

Local AI desktop workspace to build custom apps by describing them. Wandesk is an open-source AI desktop workspace that allows users to build local, custom applications simply by describing them. It functions entirely on the user's local machine with no signup required. Users can plug in any OpenAI-compatible models or tools like Claude Code, Codex, DeepSeek, OpenAI, Kimi, and Qwen. Applications built within Wandesk feature shared context, system-level AI capabilities, and persistent personal memory, allowing multiple tools like notebooks, ledgers, and chats to operate side by side cohesively.

PandasAI: Python library integrating AI into pandas for conversational data analysis and insights. PandasAI is a Python library that integrates generative artificial intelligence capabilities into pandas, making dataframes conversational. It allows users to upload various file types like PDFs, images, audio, and websites, define data points for AI-powered extraction, and see results in exportable spreadsheets with linked, highlighted sources. Users can also ask questions, plot charts, and draft reports on top of the data. It helps turn messy files into actionable data, providing real-time data insights and enhancing 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.

Powerful, modular, open-source visual AI for generating video, images, 3D, audio. ComfyUI is the most powerful and modular visual AI application and engine, serving as an open-source node-based platform for generative AI. It enables users to generate video, images, 3D, and audio using AI. The platform offers full control over AI workflows through a visual node-based canvas, allowing for branching, remixing, and real-time adjustments. Workflows are reusable, with exported files carrying metadata for easy reconstruction. Comfy Cloud, a related product, provides instant, hardware-free creative tools and custom solutions for design studios and production houses, offering access to powerful creation on demand with ready-to-use models and high-performance server GPUs.

Fully managed, scalable vector database for enterprise AI applications. Zilliz provides a fully managed vector database management system, Zilliz Cloud, powered by the open-source Milvus. It is designed for enterprise-grade AI applications, supporting billion-scale vector search, Retrieval Augmented Generation (RAG), and large language models. Zilliz aims to simplify the deployment and scaling of vector search applications by eliminating the need for complex infrastructure management.

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.

Stability AI develops open-source AI models for image, video, 3D, and audio generation. Stability AI is a company that develops cutting-edge open models in image, video, 3D, and audio generation. Their flagship product, Stable Diffusion, is a deep learning, text-to-image model used to generate detailed images conditioned on text descriptions. It can also be applied to other tasks such as inpainting, outpainting, and generating image-to-image translations guided by a text prompt. Stability AI offers various tools and platforms for deploying and utilizing their models, including self-hosted licenses, a platform API, and cloud platform integrations.

Decentralized blockchain platform for AI model execution and integration into smart contracts. Cortex is an open-source, peer-to-peer, decentralized blockchain platform that supports Artificial Intelligence (AI) models to be uploaded and executed on the distributed network. Cortex provides an open-source AI platform to achieve AI democratization where models can be integrated easily in smart contracts and create AI-enable decentralized applications (DApps). It aims to solve the problem of on-chain AI execution by utilizing the CVM (Cortex Virtual Machine) and MRT (quantization and integer-only inference).

All-in-one AI desktop app with LLM, RAG, AI Agents, running locally and privately. AnythingLLM is the ultimate all-in-one desktop AI app & assistant. It includes a built-in LLM, RAG, AI Agents, and custom tooling to improve productivity, all while running fully locally & privately on your desktop. It allows users to chat with documents, enhance productivity, and run state-of-the-art LLMs completely privately with no technical setup.

Open-source MoE AI video generation with cinematic control. Wan2.2 is the world's first open-source MoE (Mixture-of-Experts) video generation model developed by Alibaba Tongyi Lab. It enables users to create professional cinematic videos from text (text-to-video) or images (image-to-video) at 720P resolution with 24fps. Key features include advanced motion understanding, stable video synthesis, and fine-grained cinematic control over lighting, color, and composition. It is fully open-source with complete model weights, optimized for performance, and can run efficiently on consumer-grade GPUs.

Open-source LLM router for OpenClaw that optimizes model routing to save up to 70% costs. Manifest is an open-source LLM (Large Language Model) router specifically built for OpenClaw. It optimizes AI expenditures by intercepting queries and routing them to the most cost-effective model based on the complexity of the task, potentially saving users up to 70% on token costs. The system analyzes queries locally in less than 2ms to ensure minimal latency. It prioritizes privacy by performing query scoring on the user's machine and using a blind proxy architecture for its cloud version. Additionally, it allows users to track costs, set usage limits, and export data using the OpenTelemetry standard.

Open-source unified multimodal AI for understanding, generation, editing. BAGEL by ByteDance-Seed is an Apache 2.0 open-source unified multimodal model designed for advanced image/text understanding, generation, editing, and navigation. It offers capabilities comparable to proprietary systems like GPT-4o and Gemini 2.0. BAGEL can be fine-tuned, distilled, and deployed anywhere, providing precise, accurate, and photorealistic outputs through its natively multimodal architecture.

Open Source Design System starter kit with UI toolkit, component library, and AI assistant. kickstartDS is an Open Source starter kit and next-gen UI toolkit for Design Systems. It provides a low-code framework, UI development toolkit, and comprehensive component library enabling digital teams to create consistent and brand compliant web frontends super efficiently. It also offers an AI-powered Design System Concierge for expert guidance and resources.

Open-source AI Code Reviewer Agent for bug, security, and performance issue detection in code changes. Matter AI is an open-source AI Code Reviewer Agent that enables developers to review code changes focused on bugs, security vulnerabilities, and performance issues. It aims to remove up to 95% of bugs, security issues, and vulnerabilities in Pull Requests. Matter AI offers features like instant PR summaries, bug and security risk detection, faster reviewing with AI explanations, and contextual data integration from tools like Notion, JIRA, and Confluence.

Open-source tool for composing videos using HTML, CSS, and JavaScript. HyperFrames is an open-source framework, originally developed by HeyGen, that enables AI agents and developers to compose and edit videos using standard web technologies like HTML, CSS, and JavaScript. It introduces a 'Vibe-Coding' workflow where programmatic video creation is handled through code, allowing for high levels of automation and integration with AI tools. The project is licensed under Apache 2.0, making it accessible for the community to build upon and integrate into various workflows.

A free, open-source platform for AI prompt engineering, testing, and optimization. Mutatio is a free, browser-based platform designed for AI engineers, prompt writers, and developers to experiment with and refine prompts across various language models. It offers custom mutations, model flexibility and much more! Mutatio enables AI engineers to systematically test, measure, and optimize prompts with sophisticated tools. Privacy-first and community-driven. Open source, no credit card required. Free for individual use.

BreveAI: LLMs integrated with real-world data, focusing on efficiency and open-source adoption. BreveAI offers a distinctive approach to large language models (LLMs) by integrating with real-world data and prioritizing task efficiency. It emphasizes open-source adoption with an easy API. BreveAI's pricing is transparent, claiming to be 30% lower than current LLMs with 40% higher accuracy. It provides models that simplify complex tasks like prompt engineering, evaluation, RAG, fine-tuning, and deployment, allowing users to maximize AI's benefits with minimal effort. BreveAI's models are specifically trained on business language to deliver unparalleled accuracy and efficiency.

User-friendly native app to run OpenClaw AI assistant locally or in the cloud. Atomic Bot is a user-friendly native application and installer designed to run OpenClaw (Clawdbot) with ease. It allows users to set up a personal AI assistant either locally on their device for maximum privacy or in the personal cloud. Unlike traditional chatbots, Atomic Bot is built to execute real-world tasks across daily tools like Gmail, Google Calendar, and web browsers. It supports various LLM engines such as Claude, GPT, and Gemini, enabling features like persistent memory, browser automation, and scheduled workflows. It is fully open-source and designed specifically for non-technical users who want a powerful AI coworker without dealing with terminal-based setups.

Powerful 671B parameter MoE language model with state-of-the-art performance. DeepSeek v3 is a powerful 671B parameter Mixture-of-Experts (MoE) language model that offers groundbreaking performance. It is an AI-driven LLM with 671B total parameters (37B activated per token) and supports API access, an online demo, and research papers. Pre-trained on 14.8 trillion high-quality tokens, DeepSeek v3 delivers state-of-the-art results across various benchmarks, including mathematics, coding, and multilingual tasks, while maintaining efficient inference. It features a 128K context window and incorporates Multi-Token Prediction for enhanced performance and acceleration.

Open-source AI software engineer that understands instructions, researches, and generates code. Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. It is an open-source AI software engineer that uses Claude 3, GPT-4, GPT-3.5, and Local LLMs via Ollama.

Open-source voice AI platform for custom voice-controlled interfaces with a focus on privacy. Open Voice OS is a community-driven, open-source voice AI platform for creating custom voice-controlled interfaces across devices. It features NLP, a customizable UI, and a focus on privacy and security. It's designed for developers and contributors wanting to support specific devices or platforms, offering a multi-platform environment for experimenting with voice assistance technology.

Open-source low-code platform for forms, workflow automation, and analytics. formsflow.ai is a Free, Open-Source application that provides forms, workflow rules, analytics and security in an easy to use, low code platform. It helps to rapidly automate and integrate forms and business processes. It packages Form Building, Workflow Management and Analytics in one platform, allowing users to build business applications fast without coding expertise.

Open-source RAG infrastructure for building production-ready AI chat and search applications. Agentset is an open-source RAG (Retrieval-Augmented Generation) infrastructure designed to help developers build production-grade AI chat and search applications. It handles the complex aspects of RAG, including document extraction, chunking, hybrid search, and agentic reasoning, ensuring that AI apps remain reliable even with large-scale data and high user traffic. The platform is model-agnostic, allowing users to choose their own LLMs, vector databases, and embedding models. It supports over 22 file formats and multimodal data like images and tables, providing cited answers out of the box for sectors like medical AI, legal tech, and enterprise search.

Open-source desktop app combining markdown editing and terminal for Claude Code. spacecake is an open-source desktop application designed to provide a superior interface for Claude Code. It combines a Notion-style markdown editor with an integrated Ghostty terminal, bridging the gap between running terminal agents and editing documentation. The app features a real-time status bar to monitor context window usage and costs, a live task panel to track agent progress, and a WYSIWYG editor for spec-driven development. It allows users to write specs, create Mermaid diagrams, and define custom project rules via JSON to maintain coding conventions.