Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 31 of 41
A unified Python client to normalize interfaces across major LLM providers (OpenAI, Anthropic, Gemini, DeepSeek, xAI, OpenRouter).
基于Linux的一个支持多平台LLM大模型API的SDK客户端
A CLI tool to manage batch LLM calls
A unified, provider-agnostic chat completions API server that seamlessly integrates OpenAI and AWS Bedrock through a single endpoint with intelligent format detection and conversion.
Coming soon
A Gateway for LLM API interactions
Customize the LLM interface to make it compatible with the openai interface
The official Python library for the openai API
A short wrapper of the OpenAI api call.
A Python library for validating OpenAI API keys, and listing available models and verifying model access, and retrieving detailed account usage metrics.
This is a simple openAI API wrapper that makes it easier for me (and hopefully for you as well) to send messages via an assistant and manage threads locally with a custom thread key (such as message author) that is associated the thread id stored by open ai.
Polling OpenAI API without rate limit issues.
OpenAI-compatible local API server backed by Codex credentials
A tool designed to interact with APIs compatible with OpenAI's format.
Utilities for OpenAI API Calls
This Python package provides a comprehensive and efficient wrapper for the OpenAI API, designed to support advanced application development based on ChatGPT.
A light-weight, asynchronous client for OpenAI API - text completion, image generation and embeddings.
OpenAI async API with client side timeout, retry with exponential backoff and connection reuse
Async helpers for OpenAI chat
Make OpenAI batch easy to use.
Tiny, production-friendly helper for the OpenAI Batch API
An SDK for OpenAI ChatGPT batch API for a single process.
Default template for PDM package
🛠️ a command interface to the OpenAI API.
Max speed OpenAI call. Do not exceed the tpm & rpm limit.
🚀 OpenAI-Forward 是一个专为大型语言模型设计的高级转发代理,提供包括用户请求速率控制、Token速率限制和自定义API密钥等增强功能。该服务可用于代理本地模型和云端模型。OpenAI API Reverse Proxy
OpenAI HTTP Proxy is an OpenAI-compatible http proxy server for inferencing various LLMs capable of working with Google, Anthropic, OpenAI APIs, local PyTorch inference, etc.
The OpenAI Load Balancer is a Python library designed to distribute API requests across multiple endpoints (supports both OpenAI and Azure OpenAI). It implements a round-robin mechanism for load balancing and includes exponential backoff for retrying failed requests.
Local OpenAI bridge CLI for OpenAI-compatible upstreams
Speed up your OpenAI requests by balancing prompts to multiple API keys.
Python library of OpenAI API proxied by mealuet
Registry for OpenAI models with capability and parameter validation
Automatically route your prompts to the best OpenAI model
A parallel client for OpenAI API (and more)
Fastest OpenAI client — Rust core with Python bindings
Fastest OpenAI client — Rust core with Python bindings
OpenAI-Parallel-Toolkit is a Python library for handling multiple OpenAI API keys and parallel tasks. It provides API key rotation, multithreading for faster task execution, and utility functions to boost your OpenAI integration. Ideal for efficient large-scale OpenAI usage.
A multi-backend, prioritization load balancer for OpenAI
A price proxy for the OpenAI API
A thin wrapper around the OpenAI Python bindings for caching responses.
A Python module that provides rate limiting capabilities for the OpenAI API, utilizing Redis as a caching service. It helps to manage API usage to avoid exceeding OpenAI's rate limits.
CLI to manage the OpenAI Responses Server that bridges chat completions to responses API calls
A full-coverage CLI for the OpenAI REST API
openai-router
CLI to manage the OpenAI to Codex Wrapper API server
Free & Unlimited Unofficial OpenAI API Python SDK - Supports all OpenAI Models & Endpoints
Wrapper on top of openai python SDK primarily to interface with openai and anyscale public endpoints.
OpenAI API proxy for fine-grained cost tracking & control and caching of responses
Proxy Claude API requests to OpenAI-compatible backends
Slim Runner for batched OpenAI Requests
A light wrapper around the OpenAI API using apiron
Python client library for the OpenAI API
A fully typed user friendly openai wrapper package
A Python wrapper for OpenAI API interactions.
Updated the depreciating OpenAI model.
OpenAIIR → This package is now `aiir`. Install: pip install aiir
小型 JSON 封装,适配 OpenAI 风格的数据与自定义类型序列化,支持多模态图片输入
Python client library for the OpenAI API
OpenAI API
A Python package for interacting with the opengemini
easy to use openai apis
OpenGPT 3.5/4 is a project aimed at providing practical and user-friendly APIs. The APIs allow for easy integration with various applications, making it simple for developers to incorporate the natural language processing capabilities of GPT into their projects.
This package provides integration between Pydantic AI and OpenRouter, allowing you to use any model available on OpenRouter with the Pydantic AI framework. The implementation leverages the OpenAI-compatible API provided by OpenRouter.
Turn any local AI model into an OpenAI-compatible API
Groq provider for opsmate
An optimizing inference proxy for LLMs.
Supercharge your projects with LLMs. No API keys required.
Reduce AI orchestration costs by 85% with semantic caching
AWS Bedrock integration for PandaAI
LiteLLM integration for PandaAI
OpenAI integration for PandasAI
A wrapper around the Anthropic Python library
A library to transform messages for different LLMs like OpenAI, Mistral, LangChain, Gemini, DBRX, Cohere, Claude, and AWS Bedrock to Pangea messages format
CLI tool for querying multiple models with prompts from a CSV with schema support
Thin configuration helper for the Pennsieve LLM Governor — returns a pre-configured anthropic.Anthropic client.
All in one AIGC API package for Python
Unified LLM provider abstraction for Python — streaming, tool calling, extended thinking, cost tracking
统一 LLM 服务网关 - 集成 Embedding、ASR、Reranker、OCR 服务
Securely Dumping and Loading an OpenAI Client with Pickle
Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.)
A Python library for managing LLM chat models
PixelArray LLM微服务客户端
Production-grade Python client for the PixiGPT API
Unified LLM API interface for OpenAI, Gemini, Mistral, Groq, Claude, and 10+ providers
A library for easy integration with Groq API, including web scraping, image handling, and Chain of Thought reasoning
Parallel inference calls to LLM APIs using Polars dataframes with Pydantic-based structured outputs
Call LLMs, decision models, and embedding models from a Polars DataFrame using native Polars expressions.
A unified interface for querying multiple large language models
통합 LLM 팩토리 라이브러리 - 다양한 LLM 제공자를 통합된 인터페이스로 사용
Intelligent LLM Execution Layer for developer teams — anonymize code, route models, solve tickets.
Intelligent LLM Execution Layer for developer teams — anonymize code, route models, solve tickets.
LLM Proxy to reduce cost and complexity of using multiple LLMs
Anthropic Claude adapter for PULSE Protocol — send PULSE messages, get Claude responses
Google Gemini adapter for PULSE Protocol — send PULSE messages, get Gemini responses
Ollama adapter for PULSE Protocol — run local AI models with the same interface as cloud providers
OpenAI adapter for PULSE Protocol — send PULSE messages, get AI responses
`putkoff_chatGPT_API` is a Python module for interacting with OpenAI's GPT models. It simplifies the process of making API calls, managing API keys, and parsing responses, while also providing utility functions to work with timestamps and organize response data.
Minimal Python client for https://api.context.llm7.io