The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how t…

This is my personal ai assistant

True deliberative consensus MCP server where AI models debate and refine positions across multiple rounds

On-device TTS model by Neuphonic

Desktop app and Web App (Docker) that indexes videos with AI (object detection, face recognition, emotion analysis), enables semantic search through natural language queries, and generates rough cuts

Enterprise-grade Career Intelligence Platform with multi-layer validation, and fact verification. Processes 200+ documents with 100% accuracy and near zero hallucinations. ⚠️ Main branch outdated -…

Open source Loom alternative. Beautiful, shareable screen recordings.

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

Local-first AI Notepad for Private Meetings

Use your Mac trackpad as a weighing scale

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Code for the paper Hybrid Spectrogram and Waveform Source Separation

A platform to create documentation/wiki content built with PHP & Laravel

Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps

FSA/FST algorithms, differentiable, with PyTorch compatibility.

A high-performance inference engine for AI models

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

a low cost, high-workflow-efficiency, infinitely customizable platform for users to build their personal AI systems on top of in the terminal.

A library for efficient similarity search and clustering of dense vectors.

Alternative App for OMI.me

🚀 The fast, Pythonic way to build MCP servers and clients

Let Home Assistant see!

Open Source framework for voice and multimodal conversational AI

Fast and personalized local speech-to-text

Video Diffusion Model. Autoregressive, long context, efficient training and inference. WIP

🧠 100% Local Memory layer and Knowledge base for agents with WebUI

Converts text to speech in realtime