Stars
Implementation of all RAG techniques in a simpler way
The python library for real-time communication
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
Real-time webcam demo with SmolVLM and llama.cpp server
Open source AI coding agent. Designed for large projects and real world tasks.
A community-driven AI automation framework that builds upon the incredible work of the open source community. Our goal is to combine language models with specialized tools for tasks like web search…
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Open Source Alternative to NotebookLM / Perplexity / Glean, connected to external sources such as search engines (Tavily, Linkup), Slack, Linear, Notion, YouTube, GitHub and more.
A sleek web interface for Ollama, making local LLM management and usage simple. WebOllama provides an intuitive UI to manage Ollama models, chat with AI, and generate completions.
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Generate Web Pages and Components with text prompts, with Local Models. (or Cloud Models, if you want) - now supports Thinking Models!
All the demos in my Youtube Channel: Yeyu Lab
The communications platform that puts data protection first.
OrioleDB – building a modern cloud-native storage engine (... and solving some PostgreSQL wicked problems)
Home of CodeT5: Open Code LLMs for Code Understanding and Generation
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
A Beginner's Guide to Monetizing Your Python AI Chatbot
This repo contains the demos for the google agent development kit tutorial on The AI Lifestyle channel.
A cutting-edge Cascading voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.
The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
Official inference framework for 1-bit LLMs
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
In this project I designed a knowledge graph focused on Napoleon's history. I built a RAG application using this data and improved the output of LLM using the relationship between nodes
Ingesting GraphRAG from microsoft into Neo4j for local visualisation. Using their Local and Global search and comparing the results in a streamlit GUI to standard unoptimised RAG
This project demonstrates the PathRAG implementation using a team of 6 AI agents at PhD level to show how PathRAG prunes graph-based RAG using relational paths.