Khoj is described as 'Open-source platform supporting local and cloud AI chat, semantic search, document retrieval, and image generation across multiple devices and data sources' and is a AI Chatbot in the ai tools & services category. There are more than 25 alternatives to Khoj for a variety of platforms, including Mac, Windows, Web-based, Self-Hosted and Linux apps. The best Khoj alternative is Lumo by Proton, which is both free and Open Source. Other great apps like Khoj are OpenClaw, Jan.ai, AnythingLLM and Secret Llama.
Self-hosted AI workspace offering chat, tool use, and autonomous agent support. Enables email and research tasks securely on user hardware, keeps all data local, requires no external servers, and provides customizable AI workflows for privacy-focused environments.
Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.
Open-source AI assistant builds interactive chat interfaces with elements like buttons, forms, and tables, delivers over 40 tools, supports 24 AI services, local models for offline use, encrypted chat history, no ads, free usage, and privacy by design.
Complete LLM chatbot implementation, offering tokenization, pretraining, finetuning, evaluation, inference, and a simple web UI. Runs on a single 8xH100 node, features a hackable codebase, dependency-lite design, and automates the full workflow via scripts.
Ask questions to your documents without an internet connection, using the power of LLMs. 100% private, no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!
MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research.
Chat with Notion Agents anytime, anywhere.
Get answers from all your connected tools and Notion docs, databases, and projects on the go. Capture ideas with text, voice, or photos, and let agents organize them for you. Take quick actions like creating pages, drafting updates, or.
Tool for downloading AI and machine learning models from Hugging Face, Model Scope, and Civitai on Windows, featuring command line and GUI options, efficient management of large file downloads, integrity checks, and progress monitoring for users.
Custom Mac runtime allows instruction-tuned 26-billion-parameter model inference in about 2 GB RAM by streaming only required model experts from SSD, with 1.35 GB core and cache in memory. Supports 8 GB Apple Silicon Macs with CLI and native app, measured in 103 scenarios.
OptiQ is an MLX-native toolkit for running large language models on Apple Silicon. No PyTorch, no CUDA, no cloud.
Drop-In OpenAI replacement, On-device, local-first, Generate text/image/speech/music/etc... Backend Agnostic: (llama.cpp, diffusers, bark.cpp, etc...), Optional Distributed Inference(P2P/Federated).
Japan
Germany
EU
United States
Singapore
China
United Kingdom
