AIProjectPulse

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

Eureka ML Insights: Evaluation Framework for Generative Models

GitHub Stats Value
Stars 50
Forks 4
Language Python
Created 2024-07-18
License Apache License 2.0

Eureka ML Insights is a framework designed to facilitate reproducible evaluations of generative models through various benchmarks and metrics. It enables researchers and practitioners to create custom pipelines for data processing, inference, and evaluation, while also offering pre-defined evaluation pipelines for essential benchmarks. By streamlining the evaluation process, Eureka ML Insights aids in efficiently assessing capabilities such as geometric reasoning, multimodal question answering, and object recognition. This framework is a valuable tool for those aiming to conduct thorough and consistent evaluations of generative models in their research or practical applications.

frontend: Open-Source Svelte Stock Analysis Platform

GitHub Stats Value
Stars 130
Forks 29
Language Svelte
Created 2024-05-26
License GNU Affero General Public License v3.0

The ‘frontend’ project is the codebase behind stocknear, an open-source platform dedicated to stock analysis and community engagement. Built using Sveltekit for the frontend, Tailwindcss, and DaisyUI for styling, this project aims to provide a fast and simple user experience. It is designed for data enthusiasts who want to analyze stocks efficiently and interact with a community of like-minded individuals. With its open-source nature, contributors are welcome to enhance the platform by refactoring code for speed and simplicity. This project is worth exploring for those interested in robust, user-friendly stock analysis tools.

general_framework: Cross-Platform App Library with Standardized Code and CLI Support.

GitHub Stats Value
Stars 69
Forks 0
Language Dart
Created 2024-04-27
License Other

The ‘general_framework’ project is a cross-platform library designed to simplify the development of cross-platform applications using a standardized coding style similar to Flutter. This library offers several key features, including support for devices and serverless functions, a standardized code style, a CLI tool for project creation and management, and an API for integrating with bots and userbots without needing to interact with the CLI. It is highly customizable and aims to provide user-friendly information for new developers. Given its comprehensive features and ongoing development, the ‘general_framework’ is worth exploring for anyone looking to streamline their cross-platform app development process.

gerev: AI-Powered Enterprise Search Tool

GitHub Stats Value
Stars 2693
Forks 174
Language Python
Created 2023-03-05
License MIT License

Gerev is an AI-powered enterprise search engine designed to help organizations quickly locate conversations, documents, or internal pages. By integrating with popular platforms like Slack, Confluence, Jira, and Google Drive, Gerev ensures that essential information is always at your fingertips. This tool is particularly beneficial for help desk technicians who need to troubleshoot and resolve issues efficiently. With both cloud and self-hosted options, Gerev is a versatile solution that can be easily adopted by any organization looking to improve its internal search capabilities.

Humanoid-Gym: RL Framework for Sim2Real Transfer

GitHub Stats Value
Stars 688
Forks 113
Language Python
Created 2024-03-04
License -

Humanoid-Gym is a reinforcement learning (RL) framework tailored for training locomotion skills in humanoid robots. Built on Nvidia Isaac Gym, it focuses on achieving zero-shot transfer from simulation to real-world environments, ensuring that policies learned in simulation can be directly applied to physical robots without additional training. The framework also includes a sim-to-sim transfer capability, allowing users to test policies across different physical simulations to enhance their robustness and generalization. Verified by real-world tests on RobotEra’s XBot-S and XBot-L humanoid robots, Humanoid-Gym offers a practical and reliable solution for developing advanced robotic capabilities.

LightNet: Efficient Pascal AI Neural Network Library

GitHub Stats Value
Stars 50
Forks 7
Language Pascal
Created 2024-05-04
License MIT License

LightNet is an artificial intelligence neural network library implemented in pure Pascal, drawing inspiration from Darknet and YOLOv7. This library allows for the native and self-dependent execution of most Darknet models, including YOLO, without the need for external libraries. Currently, it supports training and inference on CPU, with inference speeds that often outperform optimized C CPU implementations. Optional integration with libopenblas or Intel’s Math Kernel Library can further optimize CPU performance. While it is currently under development for OpenCL, CUDA, and testing on other platforms like MacOS, Linux, and single-board computers, LightNet is already a promising tool worth exploring for AI enthusiasts and developers.