Repository History
216 repositories tagged with AI
turboseek: An Open-Source AI Search Engine Inspired by Perplexity
turboseek is an innovative open-source AI search engine developed by Nutlope, drawing inspiration from platforms like Perplexity. Built with TypeScript, it leverages advanced LLMs and search APIs to provide comprehensive answers and related follow-up questions. This project offers a robust foundation for anyone interested in building their own AI-powered search solution.
Speakr: Self-Hosted AI Transcription and Intelligent Note-Taking Platform
Speakr is a powerful, self-hosted web application for transcribing audio recordings into organized, searchable, and intelligent notes. It prioritizes privacy by running on your own infrastructure and offers advanced AI features like speaker identification, interactive chat, and semantic search. This platform is ideal for individuals and groups seeking to transform audio into actionable insights while maintaining full control over their data.
Obsidian Smart Composer: AI Chat Assistant for Contextual Notes
Obsidian Smart Composer is an AI chat assistant plugin for Obsidian designed to enhance note-taking and content creation. It offers contextual awareness, smart writing assistance, and one-click edits, allowing users to leverage their vault content for more efficient AI interactions. The plugin supports vault-aware conversations, semantic search, and integration with various AI models, including local ones.
vibe-tools: Empowering AI Agents with Teams and Advanced Skills
vibe-tools is a powerful CLI designed to enhance AI agents by providing them with an AI team and advanced skills. It integrates tools like Perplexity for web research, Gemini for repository context, and Stagehand for browser automation. Optimized for Cursor Composer Agent, vibe-tools can be utilized by any coding agent capable of executing commands.
CSM: A Conversational Speech Generation Model by SesameAILabs
CSM (Conversational Speech Model) is an advanced speech generation model from SesameAILabs, designed to create RVQ audio codes from text and audio inputs. It leverages a Llama backbone and a smaller audio decoder for Mimi audio codes, enabling high-quality, context-aware speech synthesis. The model is now natively available in Hugging Face Transformers, making it accessible for researchers and developers.
Optimum: Accelerate Hugging Face Models with Hardware Optimization
Optimum is an extension of Hugging Face Transformers, Diffusers, TIMM, and Sentence-Transformers, designed to provide a suite of optimization tools. It enables maximum efficiency for training and running models on targeted hardware, simplifying the process for developers. This library helps users achieve significant performance gains across various machine learning workflows.
bolt.diy: AI-Powered Full-Stack Web Development with Any LLM in Your Browser
bolt.diy is an open-source project that empowers developers to prompt, run, edit, and deploy full-stack web applications directly in their browser. It offers unparalleled flexibility by supporting over 19 different Large Language Models (LLMs), allowing users to choose their preferred AI for code generation and development tasks. This tool streamlines the development workflow, making AI-assisted coding accessible and highly customizable.
notesGPT: AI-Powered Voice Notes with Transcription and Summarization
notesGPT is an innovative open-source project that allows users to record voice notes and leverage AI to transcribe, summarize, and extract actionable tasks from them. Built with a modern tech stack including Convex, Next.js, and Together.ai, it streamlines the process of turning spoken ideas into organized information. This tool is ideal for anyone looking to enhance their productivity by efficiently managing their voice recordings.
Vexa: Self-Hosted Meeting Intelligence Platform with Real-Time Transcripts
Vexa is an open-source, self-hostable meeting intelligence platform designed for real-time transcription across Google Meet and Microsoft Teams. It provides a multi-user API that deploys bots to meetings, offering robust data sovereignty and flexible deployment options for various enterprise needs. Built with Python, Vexa supports real-time multilingual transcription and translation.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper2Code is an innovative multi-agent LLM system designed to automate the generation of code repositories directly from scientific papers in machine learning. It employs a sophisticated three-stage pipeline, encompassing planning, analysis, and code generation, each managed by specialized agents. This approach ensures faithful and high-quality implementations, outperforming existing baselines on relevant benchmarks.
big_vision: Google Research's Codebase for Large-Scale Vision Models
big_vision is Google Research's official codebase for training large-scale vision models using Jax/Flax. It has been instrumental in developing prominent architectures like Vision Transformer, SigLIP, and MLP-Mixer. This repository offers a robust starting point for researchers to conduct scalable vision experiments on GPUs and Cloud TPUs, scaling seamlessly from single cores to distributed setups.
NVIDIA Isaac GR00T: A Foundation Model for Generalist Robots
NVIDIA Isaac GR00T N1.6 is an open vision-language-action (VLA) foundation model designed for generalized humanoid robot skills. It enables robots to perform manipulation tasks in diverse environments by taking multimodal input, including language and images. Researchers and professionals can leverage this model for fine-tuning on custom datasets and deploying it for inference.