rezamh67
Follow
Lists (4)
Stars
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
🐍 Community-driven Python implementation of TOON
A lightweight, lightning-fast, in-process vector database
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy…
[ICLR 2026] Official PyTorch implementation for "ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding"
Fine-tuning Large Language Models (LLMs) with Quantised Low-Ranl Adaptation
[DEIMv2] Real Time Object Detection Meets DINOv3
"RAG-Anything: All-in-One RAG Framework"
Real-time webcam demo with SmolVLM and llama.cpp server
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
A smart question-answering system for Persian documents using Retrieval Augmented Generation (RAG)
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
SuperEasy 100% Local RAG with Ollama + Email RAG
Samples about using vector in SQL Server and Azure SQL
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
A modular graph-based Retrieval-Augmented Generation (RAG) system
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves
RAG Time: A 5-week Learning Journey to Mastering RAG
This repository contains the Hugging Face Agents Course.
A library for advanced large language model reasoning
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)