Open-source alternatives to Huggingface Hub

SpringBoot-Shiro-Vue is a permission management framework and role-based access control system. It provides a backend implemented with Spring Boot and a frontend built with Vue.js to manage user roles and map them to specific interface and API access rights. The project utilizes a token-based authentication system to verify user identities and enable stateless communication between the frontend and backend. It implements granular UI permission control to show or hide specific buttons and interface elements based on the current user's assigned access rights. The framework covers API security

Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai

This project is an OAuth security framework for Java web applications. It provides a set of tools for adding authentication and authorization to Spring applications using standardized delegated authorization protocols. The library implements both OAuth 1.0a and OAuth 2.0 standards. For OAuth 2.0, it includes implementations for both the client side, to request access tokens and consume protected resources, and the provider side, to issue access tokens and manage authorization grants. The framework covers API authorization workflows, securing communication between applications, and managing d

WeiXinMPSDK is a .NET software development kit designed to integrate WeChat services, official accounts, and mini programs into applications. It provides a multi-platform bot framework and a programmatic interface to interact with official, mini, and corporate accounts across the WeChat ecosystem. The project features interface-based platform abstraction and logic unification, allowing a single codebase to target multiple target platforms. It includes a messaging middleware for routing incoming requests and a distributed caching layer using providers like Redis or Memcached to synchronize ses

Misskey is a self-hosted, decentralized microblogging platform and federated social media server. It functions as a distributed content management system that allows users to communicate across multiple independent and interconnected server instances using the ActivityPub protocol. The platform distinguishes itself with a dynamic application engine that allows for the creation of interactive applications and custom page layouts using a scripting language. It also features a specialized markup language for rich text rendering, enabling the use of animations and custom styles for consistent con

mcp-atlassian is a tool that connects Atlassian project data to AI assistants using the Model Context Protocol. It provides a standardized tool-calling interface that enables AI assistants to interact directly with project data and documentation. The project supports multi-tenant environments and diverse hosting scenarios, including cloud and on-premise deployments. It implements multiple authentication methods such as OAuth 2.0, API tokens, and personal access tokens, and can route traffic through configurable HTTP, HTTPS, or SOCKS proxies to meet corporate security requirements. Its capabi

This is a Java library for creating and verifying JSON Web Tokens (JWTs), supporting multiple cryptographic signing algorithms including HMAC, RSA, and ECDSA. The library provides a builder pattern for constructing tokens with custom claims and algorithm selection, and offers separate verification methods that check signatures and validate standard claims such as expiration, issuer, and audience. The library abstracts cryptographic algorithms behind a common interface, allowing pluggable signing and verification without coupling token creation to a specific algorithm. Tokens are represented a

Sinopia is a private npm registry server used for hosting, managing, and distributing private packages and scoped modules within an internal network. It functions as a private package manager that controls access to internal code through user authentication and encrypted tokens. The system provides a caching layer that stores public registry packages locally to reduce bandwidth and improve installation speeds. It also includes a web-based interface for exploring packages, viewing documentation, and managing the state of the registry. The project covers a broad range of package management cap

Venera is a multi-source content reader and aggregator that allows users to browse and download media from various remote websites and local files through a unified interface. It functions as a local-remote media manager, synchronizing online content with local storage to enable offline viewing. The project utilizes a JavaScript-based content parser and aggregator to scrape and parse data from external web sources. This system allows for the definition of custom data extraction rules using JavaScript to fetch and display content from external websites. The platform covers remote media manage

FastHub is a native Android mobile client designed for managing GitHub repositories, issues, and pull requests. It provides a visual interface for interacting with Git version control, acting as a repository manager for editing files, tracking project milestones, and handling account administration from a handheld device. The application supports multi-account authentication, allowing users to connect via tokens or passwords to access different user profiles and enterprise accounts. It distinguishes itself with offline repository browsing, utilizing local database caching to view project data

This project is a Node.js library for implementing and managing JSON Web Tokens. It functions as a cryptographic token manager and authentication tool used to sign, verify, and decode tokens to securely transmit claims between parties. The library supports both symmetric and asymmetric signing algorithms, including HMAC and RSA. It enables the creation of digitally signed tokens using secrets or private keys, and provides mechanisms to validate token signatures and verify embedded claims such as expiration and issuer. The tool covers a range of identity and access capabilities, including sta

PocketPal AI is an on-device LLM chat application for Android that runs small language models locally, enabling private AI conversations without requiring an internet connection. It functions as an offline inference engine that downloads and executes quantized language models directly on the device, with adjustable parameters like temperature and chat templates to control how the AI behaves. The application lets users create custom AI personalities by configuring unique system prompts and contextual settings for different conversational roles. It integrates with the Hugging Face Hub to downlo

This project is a Git credential helper that automates the storage and retrieval of authentication secrets for remote repository operations. It functions as an OAuth token manager and an operating system vault storage interface to ensure authentication secrets are encrypted at rest. The tool acts as a cross-platform authentication broker, enabling the sharing of secure credentials between a host operating system and a Linux subsystem. It also serves as an enterprise proxy gateway, routing authentication traffic through corporate proxy servers to reach restricted repository endpoints. The sys

Moltworker is an AI agent sandbox and model orchestrator designed for the secure execution of untrusted code and shell commands generated by large language models. It functions as a gateway proxy that routes requests to multiple AI providers through a unified interface, integrating a container runtime backed by S3-compatible object storage to persist state across ephemeral lifecycles. The system distinguishes itself by combining an AI model orchestrator with a headless browser controller for automated web scraping and screenshot capture. It manages the full lifecycle of AI agents, including m

This project is an automated release note tool and markdown history generator that transforms repository activity into structured documentation. It functions as a GitHub API client and CI/CD pipeline component, aggregating tags, issues, and pull requests to produce categorized summaries of project changes. The tool distinguishes itself through native GitHub Enterprise integration, supporting custom API endpoints for self-hosted server instances. It employs a label-based categorization system to group changes into specific sections and utilizes personal access tokens or OAuth to manage API rat

This project is a comprehensive technical interview preparation resource and computer science interview guide. It serves as an educational reference for developers to study core software engineering fundamentals and common coding patterns required for employment screenings. The repository provides detailed guides and references covering data structures and algorithms, networking and security, operating systems, and web development. It specifically focuses on the implementation and complexity analysis of sorting, searching, and graph algorithms. The material encompasses a wide breadth of comp

Gist is a command-line interface designed for managing code snippets on remote repository services. It enables users to publish local files, clipboard content, or data from standard input streams directly to a remote service, facilitating the creation and modification of snippets without leaving the terminal. The tool distinguishes itself through its support for enterprise environments and secure authentication. It allows users to redirect operations to private or self-hosted instances by configuring custom base URLs via environment variables. Security is maintained through an OAuth device fl

Airweave is a unified AI knowledge base platform that syncs data from external APIs into a searchable layer for retrieval-augmented generation. It provides a pre-built data connector library and a framework for building custom connectors, enabling the extraction, transformation, and synchronization of structured and unstructured data from SaaS applications. The platform includes a hybrid vector retrieval system that combines semantic, neural, and keyword search strategies to deliver grounded context for AI agents. The platform distinguishes itself through an agentic search engine that iterati

FastMCP is a Python framework designed for building servers that expose functions, resources, and prompts to AI models using the Model Context Protocol. It simplifies the development process by automatically deriving tool metadata, input schemas, and documentation directly from Python function signatures and type hints. The framework provides a unified container for managing these components, allowing developers to build modular applications that integrate seamlessly with AI assistants. The project distinguishes itself through its support for interactive, server-defined user interface compone

This project is a set of deployment tools for initializing and configuring local Kubernetes environments specifically within Docker Desktop for Mac and Windows. It functions as a local cluster bootstrapper that installs essential components including the Kubernetes dashboard, ingress controllers, and the Istio service mesh. The toolkit includes a container image mirroring system that remaps registries to mirrors, allowing the environment to bypass network restrictions and accelerate image pulls during the bootstrapping process. Broad capabilities cover microservices environment setup, includ

release-it is a Git release automation tool designed to coordinate software versioning, changelog generation, and package publishing. It functions as a semantic versioning manager that increments project versions and updates configuration files based on semantic standards or custom schemes. The project distinguishes itself through a plugin-based extension system that allows for custom versioning and publishing logic. It supports complex project structures via monorepo versioning automation to synchronize internal dependencies across multiple workspaces. The tool covers a broad range of capab

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

This project is a remote file transfer server and asynchronous download orchestrator. It functions as a backend service that manages a queue of remote file transfer requests to coordinate the download of files from the web to a remote storage destination. The system operates as a distributed download coordinator, scheduling and tracking the progress of file transfers across different network nodes. It routes data requests from a client to a remote file system and utilizes asynchronous task execution to process heavy file operations in the background. The server includes capabilities for queu

CSGHub is a model management platform and dataset registry designed for storing, distributing, and managing large language models. It provides a centralized hub for AI assets accessible via a web interface, software development kit, and command line. The platform functions as a self-hosted AI infrastructure, allowing for on-premise installation within private networks for secure and offline operations. It includes a model storage system that maintains Python SDK compatibility with the Hugging Face ecosystem to facilitate the migration of existing scripts. The system covers the full model lif

SmolLM is a project dedicated to the development of small language models. It focuses on training and fine-tuning compact models that maintain high performance while utilizing fewer parameters. The project emphasizes efficient AI inference and on-device text generation, aiming to enable the deployment of lightweight models on edge devices with limited memory and processing power. It utilizes synthetic data generation to produce artificial datasets that improve the reasoning and training of these AI systems. The system supports a variety of optimization and training capabilities, including we

Binance Connector Python is a client library that provides programmatic access to the Binance cryptocurrency exchange, enabling automated trading and asset management across spot, margin, futures, and options markets. The library wraps the exchange's REST and WebSocket APIs into a Python interface with type-hinted methods, HMAC and RSA authentication, and a unified request-response pipeline for consistent error handling and rate limiting. The connector supports a broad range of exchange operations beyond core trading, including sub-account management, wallet operations, and algorithmic order

This project is an AI model API gateway and proxy server designed to provide a unified interface for interacting with diverse artificial intelligence service providers. It functions as a centralized middleware platform that routes, load balances, and translates API requests across multiple models, enabling developers to access text, image, audio, and video generation capabilities through a single, standardized integration. The gateway distinguishes itself through comprehensive administrative and financial controls, including event-driven usage accounting, real-time token consumption tracking,