OSRepos
Discover and analyze incredible open source repositories. Follow interesting projects and their updates.
Recent Repositories
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.
langcorn: Serve LangChain LLM Apps and Agents with FastAPI
Langcorn is an innovative API server designed to effortlessly deploy LangChain models and pipelines. It leverages the high-performance FastAPI framework, offering a robust and scalable solution for serving large language model applications. With features like easy installation, built-in authentication, and support for custom API keys, Langcorn streamlines the process of bringing your LLM projects to production.
mkcertWeb: A Secure Web UI for Managing Local Development SSL Certificates
mkcertWeb provides a modern and secure web interface for managing SSL certificates using the mkcert CLI tool. It simplifies the generation, download, and management of locally trusted development certificates, offering enterprise-grade security features and an intuitive user experience. This project is ideal for developers and teams needing efficient certificate handling for various environments.
maestro: Streamlining Fine-Tuning for Multimodal Models like PaliGemma 2 and Florence-2
maestro is a powerful tool designed to accelerate the fine-tuning process for multimodal models. It encapsulates best practices, handling configuration, data loading, reproducibility, and training loop setup efficiently. The project currently offers ready-to-use recipes for popular vision-language models, including Florence-2, PaliGemma 2, and Qwen2.5-VL.
Dockge: A Reactive Self-Hosted Docker Compose Stack Manager
Dockge is a sophisticated, user-friendly, and reactive self-hosted manager for Docker compose.yaml stacks. It offers an intuitive web interface for managing your Docker deployments, featuring real-time updates and an interactive editor. Designed for efficiency, Dockge simplifies the orchestration of your containerized 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.
Awesome-crawler: A Curated List of Web Crawlers and Spiders
Awesome-crawler is an extensive GitHub repository that curates a collection of web crawling and scraping tools across various programming languages. This resource is invaluable for developers looking for efficient solutions to extract data from the web. It provides a comprehensive overview of popular frameworks and libraries, making it easier to choose the right tool for any web scraping project.
Helicone: Open Source LLM Observability Platform and AI Gateway
Helicone is an open-source LLM observability platform and AI Gateway for AI engineers. It provides one-line code integration to monitor, evaluate, and experiment with large language models, offering features like cost tracking, prompt management, and intelligent routing. The platform supports a wide range of inference providers and frameworks, simplifying LLM development and deployment.
cpp-cheatsheet: A Comprehensive Modern C++ Reference Guide
The cpp-cheatsheet repository by mortennobel offers a concise and comprehensive reference for modern C++, covering C++11 and C++14 features. It serves as an invaluable resource for developers looking for quick syntax reminders and standard library usage. This cheatsheet is ideal for both learning and daily development tasks.
audapolis: An Editor for Spoken-Word Audio with Automatic Transcription
audapolis is an innovative editor designed for spoken-word audio, offering automatic transcription capabilities. It provides a word processor-like experience for media editing, making the workflow for podcasts, audiobooks, and interviews more efficient. This free and open-source tool keeps your data local, ensuring privacy and control.
KBLaM: Knowledge Base Augmented Language Models for Enhanced LLMs
KBLaM, developed by Microsoft, is the official implementation of "Knowledge Base Augmented Language Models" presented at ICLR 2025. This innovative method enhances Large Language Models by directly integrating external knowledge bases, offering an efficient alternative to traditional Retrieval-Augmented Generation (RAG) and in-context learning. It eliminates external retrieval modules and scales computationally linearly with knowledge base size, rather than quadratically.
GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
GigaSLAM is a groundbreaking monocular SLAM framework designed for kilometer-scale outdoor environments. It leverages hierarchical Gaussian splats and neural networks to achieve efficient, scalable mapping and high-fidelity rendering. This system addresses the challenges of large-scale tracking and mapping using only RGB input, extending the applicability of Gaussian Splatting SLAM to unbounded outdoor scenes.
Stay Updated
Get notified about new repositories and updates. Join our community of developers!