Repository History
354 repositories tagged with Python

KAG: Knowledge Augmented Generation for LLM Reasoning in Professional Domains
KAG is a powerful logical form-guided reasoning and retrieval framework built upon the OpenSPG engine and Large Language Models. It is specifically designed to create robust logical reasoning and factual Q&A solutions for specialized domain knowledge bases. This framework effectively overcomes the limitations of traditional RAG vector similarity calculation models and the noise often introduced by GraphRAG approaches.

PyPriompt: Python Library for Priority-Based Prompt Design
PyPriompt is a Python library for designing prompts, inspired by web design libraries like React and FastHTML. It intelligently manages context windows by using priorities to decide what information to include in the prompt, ensuring efficient use of token limits. This tool helps developers create dynamic and adaptable prompts for large language models.

Subwiz: A Lightweight GPT Model for Subdomain Discovery
Subwiz is an innovative, lightweight GPT model designed specifically for discovering subdomains. It leverages a transformer architecture, trained on extensive subdomain lists, to predict new subdomains efficiently. This tool is ideal for security researchers and developers looking to expand their subdomain enumeration capabilities.

ManimML: Visualizing Machine Learning Concepts with Manim Animations
ManimML is an open-source project that offers powerful animations and visualizations for common machine learning concepts, built upon the Manim Community Library. It aims to provide a compilation of primitive visualizations that can be easily combined to explain complex ML ideas, allowing users to focus on explanations rather than software engineering. The library simplifies the creation of engaging educational content for neural networks, convolutional layers, and more.

Horilla: A Free and Open Source HR and CRM Software
Horilla is a comprehensive, free, and open-source Human Resource Management System (HRMS) and Customer Relationship Management (CRM) software. Designed to streamline HR processes and enhance organizational efficiency, it offers a wide array of features from recruitment to payroll. Built with Django and Python, Horilla provides a robust solution for businesses looking to manage their human resources effectively.

YouCompleteMe: Advanced Code Completion and IDE Features for Vim
YouCompleteMe is a powerful, fast, as-you-type code completion and refactoring engine for Vim. It integrates multiple language servers, offering semantic completion, diagnostics, and IDE-like features across various programming languages. With its client-server architecture, it provides an enhanced coding experience directly within Vim.
DeerFlow: A Deep Research Framework Powered by LLMs and Multi-Agent Systems
DeerFlow is a community-driven Deep Research framework developed by ByteDance, designed to combine language models with powerful tools for web search, crawling, and Python execution. It enables comprehensive research processes, from intelligent clarification to report generation and even podcast creation, all while giving back to the open-source community.

GLM-4.5: Agentic, Reasoning, and Coding Foundation Models for Advanced AI
The GLM-4.5 GitHub repository introduces the GLM-4.5 and GLM-4.6 series of foundation models, designed for advanced agentic, reasoning, and coding capabilities. These models offer significant improvements, including longer context windows, enhanced coding performance, and superior reasoning, making them highly competitive in the LLM landscape. Developers can leverage these models for complex intelligent agent applications, backed by strong benchmark results.

Attachments: The Python Funnel for LLM Context and Multimodal Data
Attachments simplifies providing context to Large Language Models by transforming various file types into model-ready text and images. This Python library acts as a universal funnel, enabling developers to integrate diverse data sources like PDFs, images, web content, and even entire code repositories with just a few lines of code. It supports popular LLM APIs and frameworks, making multimodal AI development more accessible.

ROMA: Recursive Open Meta-Agents for High-Performance Multi-Agent Systems
ROMA is a powerful meta-agent framework designed for building high-performance multi-agent systems using recursive hierarchical structures. It simplifies complex problem-solving by breaking tasks into parallelizable components, offering transparent development and proven performance. This open-source framework is extensible, allowing developers to customize agents and benefit from community-driven improvements.
txtinstruct: Building Instruction-Tuned Models with Custom Data
txtinstruct is a Python framework designed for training instruction-tuned models. It focuses on supporting open data and models, enabling users to build their own instruction-following datasets and train models without licensing ambiguity. This project simplifies the process of creating custom instruction-tuned solutions.
kotaemon: An Open-Source RAG Tool for Document Chat
kotaemon is an open-source, RAG-based tool designed to facilitate interactive conversations with your documents. It provides a clean and customizable UI, catering to both end-users seeking document Q&A and developers building RAG pipelines.