Wxysnx / ai-memory-systemLinks
A high-performance, distributed memory management system for LLM agents built with LangGraph, LangChain, Ray, and vLLM. Features multi-layer memory architecture, semantic retrieval, and event-driven processing for enhanced AI conversation capabilities.
☆11Updated 9 months ago
Alternatives and similar repositories for ai-memory-system
Users that are interested in ai-memory-system are comparing it to the libraries listed below
Sorting:
- Retrieval Augmented Generation for youtube videos with a BRAD agent☆33Updated last year
- An open-source platform for building and deploying real-time, low-latency AI voice agents for call automation for marketing.☆18Updated 3 months ago
- ☆17Updated 2 years ago
- 基于DINet的推理服务，推理视频流和视频☆16Updated 2 years ago
- ☆20Updated 4 months ago
- Modify-Anything is based on yolov5,yolov8 for video and image detection. Segment-anything,lama_cleaner is applied to segment, modify, era…☆17Updated 2 years ago
- Official code and dataset release for "JAFPro: Joint Appearance Fusion and Propagation for Human Video Motion Transfer from Multiple Refe…☆14Updated 4 years ago
- BanterBot: An OpenAI ChatGPT-powered chatbot with Azure Neural Voices. Supports multilingual speech-to-text and text-to-speech interactio…☆11Updated 2 weeks ago
- Face Parsing via SegNeXt, trained on CelebAMask-HQ☆15Updated 2 years ago
- Automatically generate a lip-synced avatar based off of a transcript and audio☆14Updated 2 years ago
- Talking Face Generation system☆19Updated 2 years ago
- ☆13Updated last year
- Conversational Speaker Diarization using OpenAI AI Language Models(gpt-4) and OpenAI Whisper.☆14Updated 2 years ago
- [BMVC'24] G3FA: Geometry-guided GAN for Face Animation☆20Updated 10 months ago
- Talking head animation☆28Updated 2 years ago
- Code for "SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces" ACM MM 2023☆30Updated 2 years ago
- Multi-tenant RAG API powered by LightRAG/RAG-Anything. Auto-selects best parser (DeepSeek-OCR/MinerU/Docling) via complexity scoring☆24Updated last month
- ☆18Updated 7 months ago
- optimized wav2lip☆18Updated 2 years ago
- This project implements a Hybrid Retrieval-Augmented Generation (RAG) approach with knowledge graphs for interacting with PDF documents. …☆13Updated 4 months ago
- Text-Guided Generation of Full-Body Image with Preserved Reference Face for Customized Animation☆24Updated last year
- ☆28Updated 2 years ago
- end-to-end automated video generation pipeline designed to create engaging, TikTok-style viral short videos using AI.☆20Updated 8 months ago
- AI_Video_Shorts_Creator is a python-based tool that uses OpenAI's GPT-4 power to automatically analyze videos, extract the most interesti…☆18Updated 2 years ago
- This repository is an offical PyTorch implementation of SD-GAN: Semantic Decomposition for Face Image Synthesis with Discrete Attribute.☆13Updated last year
- Official repository of Tapir Lab.'s Lip-Sync Method☆10Updated 2 years ago
- High-performance ASR tool using Faster Whisper, supporting custom models, multi-language transcription, and real-time processing feedback…☆10Updated 4 months ago
- ☆17Updated 2 years ago
- PersonaTalk Hack☆15Updated last year
- ☆19Updated last year