Stars
Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on…
Python package for serving a local search engine. One command to download and serve a datastore---that's it 😎.
A template for building WhatsApp agents using LangGraph and Twilio. This project enables you to deploy AI agents that interact with users via WhatsApp, process messages and images, and invoke custo…
Open source and self-hostable browser automation library for AI agents
ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly
A system for agentic LLM-powered data processing and ETL
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
code for turning data sets into trading strategies
Comprehensive Vector Data Tooling. The universal interface for all vector database, datasets and RAG platforms. Easily export, import, backup, re-embed (using any model) or access your vector data …
Portfolio analytics for quants, written in Python
CompanionLLM - A framework to finetune LLMs to be your own sentient conversational companion
A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments
Supercharge Your LLM Application Evaluations 🚀
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Customizable implementation of the self-instruct paper.
An Open-source Toolkit for LLM Development
Fast & Simple repository for pre-training and fine-tuning T5-style models
Prem App it's your personal AI in your pocket
DataComp: In search of the next generation of multimodal datasets
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
🦜🔗 The platform for reliable agents.
Allows to scale the ChatGPT API to multiple simultaneous sessions with infinite contextual and adaptive memory powered by GPT and Redis datastore.
High-speed download of LLaMA, Facebook's 65B parameter GPT model
A multi-voice TTS system trained with an emphasis on quality