← all releases
Khoj AI·Jan 2, 2026·v2.0.0-beta.24·open source
Khoj
Khoj is an open-source, self-hostable personal AI assistant designed to integrate seamlessly into daily life. It enables users to interact with various large language models (LLMs) and provides functionalities such as web and document search, custom agent creation, and automation scheduling.
LLMs
overview
Khoj is an open-source, self-hostable personal AI assistant designed to integrate seamlessly into daily life. It enables users to interact with various large language models (LLMs) and provides functionalities such as web and document search, custom agent creation, and automation scheduling.
key features
- 01Model-agnostic AI assistant supporting multiple LLMs
- 02Self-hostable with options for cloud deployment
- 03Custom agent creation with tunable personality and tools
- 04Automated research and smart notifications
- 05Advanced semantic search for efficient document retrieval
related productsbrowse all →
Protenixopen sourceProtenix is an open-source, trainable PyTorch implementation of AlphaFold 3, designed for high-accuracy biomolecular structure prediction. It aims to advance accessible and extensible research tools for the computational biology community. ([github.com](https://github.com/bytedance/Protenix?utm_source=openai))Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.SINQopen sourceSINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.