Repository History
85 repositories tagged with ai
Axolotl: Streamlining LLM Fine-tuning with a Powerful Open-Source Framework
Axolotl is a comprehensive, free, and open-source framework designed to simplify the post-training and fine-tuning processes for large language models (LLMs). It offers extensive model support, diverse training methods, and robust performance optimizations, making it an invaluable tool for researchers and developers. With easy configuration and cloud-ready deployment, Axolotl empowers users to efficiently customize and enhance LLMs.
Zero: The AI Coding Agent for Your Local Terminal
Zero is an innovative AI coding agent designed for your local terminal, offering powerful capabilities to inspect repositories, edit files, run commands, and utilize browser/terminal helpers. It provides durable local sessions while giving users full control over the AI model and permission levels. This tool empowers developers with a customizable and secure AI assistant directly within their development environment.
Griptape: Modular Python Framework for AI Agents and Workflows
Griptape is a modular Python framework designed to simplify the development of generative AI applications. It provides a flexible set of abstractions for working with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and various other AI components. With its structured approach, Griptape enables developers to build sophisticated AI agents and workflows efficiently.
Memoripy: An AI Memory Layer for Context-Aware Applications
Memoripy is a Python library designed to provide an AI memory layer for context-aware applications. It offers both short-term and long-term storage, semantic clustering, and optional memory decay. This robust tool helps AI systems manage and retrieve relevant information efficiently, supporting various LLM APIs like OpenAI and Ollama.
torchchat: Run PyTorch LLMs Locally on Servers, Desktop, and Mobile
torchchat is a PyTorch-native codebase designed to showcase the ability to run large language models (LLMs) seamlessly across various platforms. It enables local execution of LLMs using Python, within C/C++ applications on desktop or servers, and directly on iOS and Android devices. Although no longer under active development, it remains a valuable resource for understanding and implementing local LLM deployment strategies.
Docling: Streamline Document Processing for Generative AI Applications
Docling is a powerful Python library designed to simplify document processing, preparing diverse formats for generative AI applications. It offers advanced parsing capabilities, including sophisticated PDF understanding, and provides a unified document representation. With seamless integrations into the AI ecosystem, Docling empowers developers to build robust AI solutions.
DeepFabric: High-Quality Synthetic Data for Agentic AI Systems
DeepFabric is an open-source Python library designed to generate high-quality synthetic training data for language models and agent evaluations. It excels at creating domain-specific datasets that teach models to think, plan, and act effectively, including correct tool usage and adherence to schema structures. This comprehensive pipeline also integrates training and evaluation capabilities, ensuring robust model development.
OpenMontage: The First Open-Source, Agentic Video Production System
OpenMontage is the world's first open-source, agentic video production system, designed to transform your AI coding assistant into a full video production studio. It features 12 pipelines, 52 tools, and over 500 agent skills, enabling end-to-end video creation from a simple prompt. This powerful tool handles research, scripting, asset generation, editing, and final composition, including the unique ability to produce real video from stock footage.
Guardrails: Enhancing LLM Reliability and Structured Data Generation
Guardrails is a Python framework designed to build reliable AI applications by adding guardrails to large language models. It helps detect, quantify, and mitigate risks in LLM inputs/outputs, and facilitates the generation of structured data. This framework ensures more predictable and safer interactions with AI models.
OpenPencil: The AI-Native, Open-Source Figma Alternative Design Editor
OpenPencil is an innovative AI-native design editor, serving as a powerful open-source alternative to Figma. It supports .fig files, integrates AI for design creation, and provides a fully programmable toolkit with a headless Vue SDK. This project emphasizes real-time collaboration and local data control, making it a compelling choice for designers and developers seeking flexibility and ownership.
REAL Video Enhancer: AI-Powered Video Interpolation, Upscaling, and Denoising
REAL Video Enhancer is a powerful open-source application designed to enhance video quality across Linux, Windows, and macOS. It leverages AI models for advanced video processing tasks such as frame interpolation, upscaling, decompression, and denoising. This tool provides a modern alternative to older software, making high-quality video enhancement accessible to a wider audience.
Open-LLM-VTuber: Your Offline, Cross-Platform AI Companion with Live2D
Open-LLM-VTuber is an innovative open-source project that brings a customizable, voice-interactive AI companion to your desktop. It supports real-time voice interaction, visual perception, and dynamic Live2D avatars, all running completely offline across Windows, macOS, and Linux. This project allows users to create a personalized AI companion with extensive model support and advanced interaction features, ensuring privacy and flexibility.