Lists (3)
Starred repositories
Visual testing tool for MCP servers
A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous soci…
This repository contains the python scripts developed as a part of the work presented in the paper "Auditory Attention Detection via Cross-Modal Attention"
This repository provides the Python code to reproduce the ISCA Interspeech 2023 paper entitled "BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Mu…
Chrome DevTools for coding agents
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
📑 PageIndex: Document Index for Reasoning-based RAG
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
Deploy serverless AI workflows at scale. Firebase for AI agents
Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
Core building blocks for AI apps. High-quality, accessible, and customizable components for AI interfaces.
An open source collection of animated, interactive & fully customizable Vue components for building stunning, memorable websites.
Deepagents is an agent harness built on langchain and langgraph. Deep agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped …
Jinx is an enterprise-grade autonomous engineering agent that converts natural-language intent into working software. It generates and executes code safely in a sandbox, leverages durable memory an…
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation