Provides unmatched realistic motion and fluid human action with prompt adherence for customizable AI-generated video simulations.


Provides unmatched realistic motion and fluid human action with prompt adherence for customizable AI-generated video simulations.


Doco is an AI-native writing assistant built for Microsoft Word. Reference any file, run adaptive workflows, and insert accurate, fully formatted content—without leaving your doc. Perfect for proposals, policy, education, and enterprise teams.




Minimal, clean full-stack LLM chatbot, running tokenization, pretraining, finetuning, evaluation, inference, and web UI on a single 8xH100 node.

xPrivo is a free, open-source, private AI chat assistant that focuses entirely on keeping you anonymous while helping tackle your most complex questions.




AI generative user interface system produce copy-paste-ready React code via easy text prompts, built with shadcn/ui and Tailwind CSS.


Terminal UI for personal finance with Plaid sync, CSV import, asset tracking, customizable categorization rules, keyboard navigation, tagging, and financial trends.




Moshi is an innovative AI chatbot with advanced voice recognition, real-time interaction, and dual audio streams, setting up a new standard for voice-based chatbots.




Instantly find files, apps, and web pages with a unified search interface. Access major engines like Google and Bing. Switch seamlessly between local and online content.




Lightning-fast completions, deep code understanding, and agentic software engineering—right where you work.




Customizable virtual assistant with voice chat, web search, document interaction, file management, extension support, and flexible AI model options.




On-device speech recognition tool with real-time transcription, command recognition, speaker identification, low word-error rates, and multi-language support.
Personal AI companion with long-term memory for secure journaling, empathetic conversations, personalized advice, continuous learning, and private self-reflection.




Harness Google's knowledge, voice recognition, and AI art creation in conversations with a chatbot rich in real-time information, versatile sharing, and API connectivity.




Interactive modules leverage AI for grammar, slang, and object labeling. Personalized practice includes audio pronunciation, contextual scenarios, and translation features.



Visual programming environment for building, debugging, and deploying LLM agent workflows with real-time collaboration, YAML-based version control, and TypeScript integration.

Instead of generating images with long, detailed text prompts, Whisk lets you prompt with images. Simply drag in images, and start creating.




DeepL Agent is a general-purpose AI agent designed to autonomously handle a wide range of business tasks through natural language instructions. From building and researching sales account lists, to translating and publishing website content – it's built to streamline the...




Self-hosted coding agent platform with voice support, Git worktree integration, and multi-provider compatibility. Access from phone, desktop, or terminal.




Open source generative AI video model transforming text and images into cinematic scenes, offering 14 and 25 frame options with flexible frame rates for creative, educational, and media applications.


AI-powered grammar checker for Mac that processes everything locally with zero data collection, ensuring total privacy, instant offline results, and seamless integration across applications.




AgentGPT allows you to configure and deploy Autonomous AI agents. Name your own custom AI and have it embark on any goal imaginable. It will attempt to reach the goal by thinking of tasks to do, executing them, and learning from the results.




Diffusion-based AI generates high-quality, photorealistic images closely aligned with user prompts, accessible through API integration with Google Cloud Vertex AI.



A large language model tool developed by AMD, offering superior performance with open access to weights and data, bridging gaps in AI model advancements.


AI assistant with hybrid-attention reasoning, multi-step task handling, lightning chat, deep research, multimodal generation, privacy and cross-platform sync.




Transform your social profile into a unique voice using ElevenLabs Voice Design API, showcasing the creative potential with fully open-source tools.

