Open-source alternatives to Openai Api Proxy

Yoga is a GraphQL server framework and runtime-agnostic HTTP handler used to build and deploy GraphQL APIs. It functions as a toolkit for managing schemas and resolvers, providing a spec-compliant environment for hosting APIs across diverse JavaScript runtimes, including Node.js, Deno, Bun, and serverless cloud environments. The project distinguishes itself through its ability to act as an Apollo Federation gateway, composing multiple subgraphs into a single unified supergraph. It also serves as a dedicated subscription server, delivering real-time data streaming via both WebSockets and Serve

Hono is a minimal JavaScript HTTP framework designed for building web servers across multiple runtimes, including Node.js, edge runtimes, and serverless platforms. It functions as a cross-runtime web server and a web standard API wrapper, normalizing various runtime request and response objects into standard Web API signatures. The project serves as an HTTP middleware orchestrator and request handler, utilizing a middleware-based request pipeline and hierarchical route mounting to create modular server structures. It distinguishes itself through a runtime-agnostic event wrapper that ensures c

gpt4free-ts is a TypeScript-based LLM API proxy and gateway that provides a unified interface for accessing large language models without paid subscriptions or official API keys. It functions as a containerized AI bridge that routes requests to various free third-party providers to retrieve chat completions. The project acts as an OpenAI API wrapper, translating requests and responses into the standard OpenAI chat completions format to ensure compatibility with existing AI tools. It utilizes a provider-based routing system to distribute request loads across available endpoints. The gateway s

LLM Guard is a security firewall and guardrail framework designed to scan and sanitize inputs and outputs for large language models. It functions as a proxy gateway and security layer to block prompt injections, toxicity, and sensitive data leakage while ensuring that model interactions remain compliant with organizational policies. The system distinguishes itself through a modular scanner pipeline that utilizes local model orchestration to eliminate external network dependencies. It supports real-time security filtering via streaming chunk analysis and implements a fail-fast execution model

Tinyproxy is a lightweight HTTP and HTTPS proxy daemon designed for POSIX operating systems. It functions as a system-level network proxy that manages web traffic with minimal resource overhead. The project supports multiple routing modes, including reverse proxying to forward requests to backend servers and transparent proxying to intercept network traffic without client-side configuration. It also includes a header filter to modify or block specific HTTP headers for privacy and security. The software incorporates network access control based on client subnets and protocol filtering. For sy

webpack-dev-server is a local web server designed to serve webpack bundles and trigger browser refreshes when source files change. It functions as a development environment that hosts bundled applications and provides a live reloading workflow. The project distinguishes itself by supporting hot module replacement to update modules in a running application without a full page reload. It also acts as an HTTP proxy to redirect network request paths to different backends and provides history API fallbacks specifically for hosting single-page applications. The server includes capabilities for mon

Mercure is an HTTP-based message broker and real-time pub/sub server that routes asynchronous data updates to authorized subscribers. It functions as a centralized hub that receives data via standard HTTP requests and broadcasts it to web clients using the Server-Sent Events protocol. The project distinguishes itself by replacing WebSockets with a unidirectional HTTP connection, leveraging HTTP/2 and HTTP/3 for multiplexed, low-latency delivery. It implements a secure access control layer using JSON Web Tokens and JSON Web Signatures to validate the identity of publishers and subscribers, and

Nitter is a privacy-focused, alternative web interface for viewing public social media content. It functions as a server-side proxy that fetches and renders external posts, allowing users to browse content without requiring a personal account or executing third-party tracking scripts. By stripping away user identifiers and tracking mechanisms, the application provides a lightweight, anonymous viewing experience. The project distinguishes itself through its emphasis on network-level privacy and self-sovereignty. It supports routing traffic through Tor and I2P networks to bypass censorship and

ServiceStack is a high-performance .NET web framework designed for building type-safe APIs using strongly-typed request and response objects. It functions as a message-based API engine that decouples business logic from the transport layer, allowing services to be exposed via multiple protocols including HTTP, gRPC, and various message queue providers. The framework is distinguished by its type-safe API generator, which produces native client SDKs and data transfer objects from service metadata across multiple languages. It also includes a distributed service gateway for microservices orchest

Qui is a BitTorrent cross-seeding manager, automation engine, and multi-instance torrent dashboard. It provides a unified web interface to manage multiple separate torrent client instances from a single location and functions as an authentication gateway using OpenID Connect to protect backend API endpoints. The project specializes in identifying and adding matching torrents across different trackers to increase seeding ratios. It utilizes hardlink-based file replication to satisfy multiple tracker layouts without duplicating disk space and features a rule-based automation engine that execute

mcp-context-forge is a Model Context Protocol federation gateway that unifies diverse AI tool servers and APIs into a single consistent interface for discovery and execution. It acts as a centralized proxy that aggregates multiple servers and APIs, allowing AI agents to access and invoke a unified set of tools, prompts, and resources. The project distinguishes itself through a multi-protocol translation bridge that converts communication between standard I/O, SSE, gRPC, and REST to enable interoperability between disparate tool servers. It includes a comprehensive LLM evaluation framework for

Azure Docs is the official technical documentation repository for Microsoft Azure, the cloud computing platform. It provides comprehensive guidance on the full spectrum of Azure services, covering everything from core infrastructure components like virtual machines, Kubernetes clusters, and serverless computing to platform services for AI, machine learning, data analytics, and storage. The documentation details how to provision, manage, and govern cloud resources at scale, including policy enforcement, identity management, and cost optimization. The documentation distinguishes Azure through i

This repository serves as an educational resource and technical guide for developers learning to integrate large language models into software applications. It provides practical lessons and code examples focused on building systems that perform automated text generation, data analysis, and interactive chat tasks. The project functions as a framework for understanding how to connect applications to external artificial intelligence services. It covers the implementation of secure authentication, the orchestration of network requests, and the configuration of model parameters such as temperatur

GraphQL Yoga is a GraphQL server framework designed for building APIs that operate across all JavaScript environments. It utilizes the WHATWG Fetch API to provide a standardized request and response interface, enabling the server to run on serverless and edge computing platforms. The framework includes a specialized server for processing file uploads via the standard GraphQL multipart request specification and a subscription server that delivers real-time data streaming through server-sent events. An extensible plugin framework allows for the injection of custom behaviors and logic into the r

This project is a legal AI system that provides a language model assistant grounded in a retrieval-augmented generation knowledge base. It enables users to perform vector-based legal searches and receive grounded answers to legal questions. The system specifically supports Chinese legal knowledge retrieval by converting markdown documents into vector embeddings for semantic search. It utilizes a streaming web interface that delivers incremental AI responses via server-sent events. The broader capability surface includes chunk-based document processing, vector-based knowledge indexing, and si

openai-go is an LLM SDK for Go and a client for interacting with OpenAI services. It provides type-safe bindings to generate text, images, and audio via REST endpoints, enabling the integration of large language models and AI assistant orchestration into Go applications. The library serves as an agent orchestration tool for managing stateful conversation threads and autonomous agents with integrated tool calling and file search. It also functions as an asynchronous batch processing client for monitoring large-scale request groups and fine-tuning jobs, alongside a management SDK for controllin

exllamav2 is a high-performance inference engine and framework for executing large language models locally on consumer-class GPUs. It provides a complete system for local model deployment, including a specialized inference engine and tools for model quantization. The project features a multi-GPU inference framework that distributes workloads across multiple graphics cards to run models that exceed the memory capacity of a single device. It includes a GPU model quantizer capable of converting models into mixed-precision formats between 2 and 8 bits to balance memory usage and accuracy. The en

Fireplexity is an AI-powered search engine designed to retrieve real-time web data and synthesize it into comprehensive, conversational answers. It functions as a search application that integrates automated web crawling to aggregate information from multiple online sources, grounding its responses in current internet content. The platform distinguishes itself through a focus on transparency and responsiveness. It provides verifiable citations and direct links to original source material for every generated answer, allowing users to confirm the accuracy and context of the information provided

This project is a PHP API client and SDK for integrating OpenAI services into PHP applications. It serves as an integration library and wrapper for interacting with large language models to generate text, images, and audio via REST API calls. The library provides specialized orchestration for AI assistants, managing conversation threads and vector stores. It also includes tools for custom model fine-tuning, semantic search implementation through text embeddings, and audio processing for transcription and synthesis. The capability surface covers content moderation, file management, and the ha

Apollo Kotlin is a strongly-typed GraphQL client and code generation library designed for Kotlin and JVM applications. It functions as a comprehensive development tool that transforms GraphQL schema definitions and query documents into type-safe models during the build process, ensuring that data access errors are identified at compile time rather than at runtime. The project distinguishes itself through its multiplatform runtime abstraction, which allows developers to share data fetching and caching logic across Android, iOS, and desktop environments. It provides a normalized local caching s

SafeLine is a containerized web application firewall and reverse proxy designed to secure web services by inspecting incoming HTTP traffic. It acts as a security gateway that sits in front of backend infrastructure to filter malicious requests and enforce access policies before they reach the application server. The platform distinguishes itself through advanced bot mitigation and content protection capabilities. It employs challenge-response mechanisms to verify human users and dynamically obfuscates HTML and JavaScript content to prevent unauthorized scraping and code tampering. These featu

This project serves as a comprehensive technical guide and framework for building, deploying, and managing event-driven applications. It focuses on serverless architecture development, providing patterns and practices for implementing cloud-native services that execute code in response to triggers without requiring persistent server infrastructure. The repository distinguishes itself by offering a unified approach to polyglot runtime orchestration, allowing developers to manage components written in multiple programming languages within a single project. It emphasizes local cloud emulation, e

Salvo is a comprehensive Rust web framework for building asynchronous HTTP servers and web applications. It features a hierarchical web router that uses a tree-based structure to map requests to handlers and an asynchronous middleware pipeline based on the onion model for request and response pre- and post-processing. The framework is distinguished by its native support for modern network protocols, including a QUIC-based HTTP/3 implementation alongside HTTP/1 and HTTP/2. It includes an integrated OpenAPI documentation generator that extracts schemas directly from handler signatures to produc

This project is a serverless framework for deploying Telegram bots that interface with large language models and AI image generators. It functions as an edge-based orchestrator and gateway that routes messages between the Telegram API and various AI service providers using a stateless architecture. The system enables the management of multiple bot instances and allows for the dynamic switching of AI models and system prompts within a single chat interface. It distinguishes itself through a modular plugin system that allows for the injection of custom logic and specialized behaviors into the m

Inngest is a durable execution framework and event-driven automation engine designed to orchestrate background workflows. It enables developers to build resilient, stateful processes by memoizing function steps, ensuring that long-running tasks can automatically resume from the last successful operation after failures, timeouts, or infrastructure restarts. The platform distinguishes itself through its event-driven architecture, which uses a schema-validated bus to trigger functions and coordinate complex, multi-step logic. It employs an onion-model middleware approach for cross-cutting concer

Oak is a cross-runtime HTTP middleware framework and web server designed to operate across Deno, Node.js, Bun, and Cloudflare Workers. It provides a unified system for building APIs and web servers using a sequential chain of middleware functions and a hierarchical routing engine that maps URL paths to handlers via a nested tree structure. The framework includes a runtime-agnostic serverless adapter that translates diverse cloud provider events into a standard request and response interface. It also features a dedicated WebSocket server implementation for bidirectional real-time communication

Nuclio is a high-performance serverless framework designed for Kubernetes that automatically executes user functions when events arrive from HTTP endpoints, message queues, or streaming data platforms. It processes hundreds of thousands of events per second per function instance through efficient parallel workers, and can allocate functions to run on either CPU or GPU hardware to match workload requirements for data processing or machine learning tasks. The platform scales function instances down to zero when idle and wakes them on demand based on incoming event load, while providing an event