AIProjectPulse

Discover the most innovative AI and machine learning projects from GitHub.

Council: AI Agent Platform for Scalable Control

GitHub Stats Value
Stars 814
Forks 33
Language Python
Created 2023-07-10
License Apache License 2.0

Council is an open-source platform designed for the rapid development and robust deployment of customized generative AI applications. It utilizes teams of agents built in Python (and soon in Rust) to extend the Large Language Model (LLM) tool ecosystem. Council enhances AI agent management by providing advanced control and scalable oversight through features like Controllers, Filters, Evaluators, and Budgets. This enables automated routing between agents, comparison, evaluation, and selection of the best results for tasks. The platform integrates with various LLMs and popular libraries such as LangChain, making it a valuable tool for those looking to create sophisticated AI applications with predictable behavior.

data-centric-AI: Curated Resource List for AI Developers

GitHub Stats Value
Stars 1026
Forks 72
Language
Created 2023-03-07
License -

The ‘data-centric-AI’ project is a curated collection of resources focused on the principles and practices of data-centric artificial intelligence. This initiative aims to highlight a diverse range of ideas and techniques in the field, rather than attempting to be exhaustive. It includes survey papers, perspective papers, and tutorials such as the Large Time Series Model (LTSM) and a KDD 2023 tutorial on data-centric AI techniques. The project welcomes contributions to enhance and refine the list, making it a valuable resource for those interested in the evolving landscape of data-centric AI.

Generative AI Docs: Gemini API Tutorials & Demos

GitHub Stats Value
Stars 1610
Forks 560
Language Jupyter Notebook
Created 2023-04-06
License Apache License 2.0

The ‘generative-ai-docs’ project is a comprehensive resource for developers working with the Google Gemini API and Gemma. It houses a wealth of documentation, including guides, tutorials, notebooks, and code examples that are directly used on the ai.google.dev website. The project is organized into sections such as demos, which feature fully functional applications, and examples, which provide smaller, single-purpose code snippets to illustrate specific concepts. Whether you’re looking to contribute to the documentation or maintain demo apps, this project offers valuable resources and clear guidelines for participation. It is licensed under the Apache License 2.0.

glanceables: Simplified Web Widgets for Essentials

GitHub Stats Value
Stars 46
Forks 1
Language Swift
Created 2024-05-31
License GNU General Public License v3.0

Glanceables is a project designed to simplify your web experience by transforming complex websites into easy-to-digest widgets. It operates on the principle of “A browser that’s not a browser,” providing you with only the essential information you need, such as price changes, campground availability, or traffic updates, without the hassle of constantly refreshing pages. By stripping away ads and complicated layouts, Glanceables aims to make your digital life easier and more enjoyable, bringing back the joy of browsing by delivering just the good stuff. This approach helps you navigate the internet with precision and ease.

Llama Recipes: Scalable Library for Fine-Tuning Meta Llama Models

GitHub Stats Value
Stars 11655
Forks 1658
Language Jupyter Notebook
Created 2023-07-17
License -

The ’llama-recipes’ project is designed to facilitate the use of Meta’s Llama models, specifically the latest version, Llama 3.1. This repository provides a comprehensive library for fine-tuning these models, along with practical example scripts and notebooks. It aims to help users quickly get started with various applications, such as domain adaptation and building large language model (LLM) based solutions. The examples cover running Llama models locally, in the cloud, and on-premises, making it a valuable resource for anyone looking to leverage the capabilities of Meta’s Llama models in different scenarios.

LlamaChat: Local Chat App for LLaMA Models on Mac

GitHub Stats Value
Stars 1453
Forks 57
Language Swift
Created 2023-03-26
License MIT License

LlamaChat is a macOS application designed to enable users to interact with popular AI models such as LLaMA, Alpaca, and GPT4All directly on their Mac. This app supports both Intel and Apple Silicon processors and requires macOS 13 Ventura. By running these models locally, users can engage in conversations without relying on cloud services, ensuring privacy and offline capability. LlamaChat is worth exploring for those interested in AI technology and wanting to leverage these advanced models in a convenient and secure manner.