Repository History
76 repositories tagged with ai
mcp-ui: Building Interactive UIs for AI with Model Context Protocol
mcp-ui is an SDK that enables the creation of rich, interactive user interfaces for AI tools, built on the Model Context Protocol (MCP). It standardizes UI delivery over the protocol, allowing developers to craft next-gen UI experiences. This project provides client and server SDKs in multiple languages, making it easier to integrate dynamic UIs into AI applications.
TTSFM: OpenAI-Compatible Text-to-Speech API Service (Project Notice)
TTSFM was a project designed to mirror OpenAI's TTS service, offering a compatible API for free text-to-speech conversion with multiple voice options. Built on the openai.fm backend, it provided a Python SDK, RESTful API, and a web playground for easy testing and integration. Please note, the project is no longer functional as the openai.fm demo website has been shut down.
Chat UI: The Open Source Interface for LLMs, Powering HuggingChat
Chat UI is an open-source SvelteKit application that provides a flexible chat interface for Large Language Models (LLMs). It serves as the foundation for HuggingChat, enabling users to interact with various OpenAI-compatible APIs. This project offers extensive customization and deployment options, making it ideal for developers building their own AI chat experiences.
PETSA: Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
PETSA offers a parameter-efficient solution for Test-Time Adaptation (TTA) in time series forecasting, addressing the performance degradation caused by non-stationary data. It adapts pre-trained models during inference by updating small calibration modules, reducing memory and compute costs. This method, which includes low-rank adapters, dynamic gating, and a specialized loss, improves forecasting accuracy across diverse backbones and datasets.
ai-llm-comparison: Compare AI Models and Pricing Easily
ai-llm-comparison is a free, open-source web application designed to help users compare various AI language models from different providers. It offers features like price comparison, a pricing calculator, and side-by-side model comparisons, making it easier to find the best AI model for specific needs. This tool is invaluable for developers, businesses, and researchers navigating the complex landscape of AI services.
claude-code-forge: Access Any AI Model Through Claude's Interface
claude-code-forge is a utility that enables users to access a wide array of AI models through the Claude Code interface. By configuring Claude Code to use TensorBlock Forge as its API provider, developers can leverage models like Qwen Coder and Gemini, expanding beyond Claude's default offerings. This repository provides simple setup scripts to integrate TensorBlock Forge seamlessly.
Company Research Agent: Deep Diligence with Multi-Agent AI and LangGraph
The Company Research Agent is an advanced tool designed for in-depth company diligence, leveraging a multi-agent framework built with LangGraph and Tavily. It efficiently gathers, filters, and synthesizes information from various sources. The system utilizes Google's Gemini 2.5 Flash for high-context synthesis and OpenAI's GPT-5.1 for precise formatting, delivering comprehensive research reports.
Gitingest: Transform GitHub Repositories into LLM-Friendly Code Extracts
Gitingest is a powerful tool designed to convert Git repositories into prompt-friendly text for Large Language Models (LLMs). It allows developers to easily obtain structured code extracts, making it simpler to feed codebase context into AI applications. With Gitingest, you can quickly generate digests from GitHub URLs or local directories, streamlining your AI-driven development workflows.
DataTrove: Streamlining Large-Scale Data Processing for LLMs
DataTrove is a powerful Python library designed to simplify the complex task of processing, filtering, and deduplicating text data at a massive scale. It offers a collection of customizable, platform-agnostic pipeline blocks, making it ideal for preparing training data for large language models. With support for various execution environments, DataTrove frees developers from scripting madness, enabling efficient and reproducible data workflows.
Cactus: Cross-Platform AI Inference Engine for Mobile Devices
Cactus is an open-source project providing an energy-efficient, cross-platform AI inference engine specifically designed for mobile devices. It features low-level ARM-specific SIMD operations, a unified zero-copy computation graph, and a high-level transformer engine with NPU support. This framework enables developers to deploy state-of-the-art AI models on smartphones and other edge devices with impressive performance.
POML: Structured Prompt Engineering for LLMs with a Markup Language
POML (Prompt Orchestration Markup Language) is a novel markup language developed by Microsoft for advanced prompt engineering. It brings structure, maintainability, and versatility to LLM applications by addressing common challenges like unstructured prompts and complex data integration. Developers can systematically organize prompt components, integrate diverse data types, and manage presentation variations for more sophisticated and reliable LLM interactions.
AI File Sorter: Organize Your Files with Local AI and Visual LLMs
AI File Sorter is a powerful cross-platform desktop application designed to automate file organization using AI. It leverages local LLMs for privacy-first categorization and can even suggest better filenames for images based on their visual content. This tool helps reduce clutter and improve file discoverability across various storage locations.