Stars
Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.
Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows
utilities for decoding deep representations (like sentence embeddings) back to text
Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)
Easily fine-tune, evaluate and deploy Qwen3, DeepSeek-R1, Llama 4 or any open source LLM / VLM!
Grid: Private Location Sharing mobile app for iOS/Android. E2EE with Matrix.
Repository of the paper "Do Language Models Plagiarize?", Proceedings of the ACM Web Conference 2023
Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).
Label Studio is a multi-type data labeling and annotation tool with standardized output format
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Fit interpretable models. Explain blackbox machine learning.
🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…
The simplest way to run LLaMA on your local machine
Interact with your documents using the power of GPT, 100% privately, no data leaks
A manifest v3 web extension with minimal permissions to automatically redirect to privacy friendly frontends. ⭐️ Star to support our work!
MemoryCache is an experimental development project to turn a local desktop environment into an on-device AI agent
🐢 Open-Source Evaluation & Testing for AI & LLM systems
ditto: WAN Traffic Obfuscation at Line Rate (source code belonging to the NDSS 2022 paper)
Priveedly: A django-based content reader and recommender for personal and private use
NewsBlur is a personal news reader that brings people together to talk about the world. A new sound of an old instrument.
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
audible feedback on just how much your browsing feeds into google