Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 32 of 41

py-gpt-interface

A simple interface for using the GPT API.

py-llm-core

PyLLMCore provides a light-weighted interface with LLMs

py-llmify

A minimal, fast, and type-safe Python library for LLM chat completions across multiple providers

py-simpllm

Simple LLM wrapper library

pyChatGPT

An unofficial Python wrapper for OpenAI's ChatGPT API

pyChatGPT-intl

This Python3 module acts as a wrapper for ChatGPT API and will help you to use ChatGPT in your own language.

pyChatGPTH

An unofficial Python wrapper for OpenAI's ChatGPT API for HEROKU

pyGPT-api

An unofficial API allowing free interaction with ChatGPT in Python

pydantic-ai-litellm

LiteLLM model integration for Pydantic AI framework - access 100+ LLM providers through a unified interface

pydantic-ai-unofficial-models

A collection of unofficial models for pydantic-ai

pydantic-ai-web-models

A lightweight Pydantic AI model provider that routes requests to web-based LLMs (OpenAI, Google) through Temporal workflows.

pygptwrapper

Python Wrapper for the ChatGPT API

pyhub-llm

Standalone LLM library with support for multiple providers

pyllmlib

A Simple Unified LLM API interface for OpenAI, Gemini, Mistral, Groq and more.

pyllmlink

Python wrapper that downloads and launches the llm-link binary

pyllms

Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google, Mistral, OpenRouter, Reka, Groq, Together, Ollama, AI21, Cohere, Aleph-Alpha, HuggingfaceHub), with a built-in model performance benchmark.

pyprocessors-openai_completion

OpenAICompletion processor

python-claude-api

The python package that returns Response of Anthropic Claude through API.

python-fastllm
python-gemini-api

The python package that returns Response of Google Gemini through API.

python-gemini-multi-api

The python package that returns Response of Google Gemini through API.

python-jsonllm

LLM please cast to JSON

python-llm

An LLM wrapper for Humans

python-llm-factory

A flexible Python factory for working with multiple Large Language Model (LLM) providers (OpenAI, Anthropic, Gemini, Llama) using a unified interface, with robust configuration and extensibility.

python-mistralclient

Mistral Client Library

pythonGPT3

"The ChatGPT Requests module is a Python package that provides a convenient interface for making requests to the ChatGPT language model."

pythongardenerpersonalpkg-openai-api-key-chatgpt-api-key

A simple example package with openai api key

quackamollie-langchain-model-manager

Model manager compatible with Langchain models for Quackamollie Telegram chat bot

quackamollie-llama-index-model-manager

Model manager compatible with Llama-Index models for Quackamollie Telegram chat bot

qualtop-llmapi

Experimental libraries for communication with LLMs.

quickgpt

A barebones library to make interacting with OpenAI's ChatGPT API much simpler.

qwen-claude

Qwen + Claude Code Router bootstrapper

qx-llms

A simple LLM client factory utility for use across QX applications

rateLLMiter-ai

LLM ratelimiter for Python.

re-gpt

Unofficial reverse-engineered ChatGPT API in Python.

reflex-llms

Python package for autofallback to local LLMs if OpenAI API or Azure Endpoint is not available

relay-llm

Multi-provider LLM batch prediction library

reliableGPT

Error handling and auto-retry library for GPT

remote-llm

Remote LLM

rethink-llmhub

LLMHub CLI — manage LLM specs and runtime configs

rethink-llmhub-runtime

A lightweight runtime for LLMHub that delegates to any-llm

rezunate-llm-sdk

Unified Python SDK for chat completions across multiple AI providers

ritellm

A fast LLM gateway

robust-llm-chain

Production-grade cross-vendor failover for LLM APIs

rosetta-llm

Multi-format bidirectional LLM proxy — translates between OpenAI Chat, OpenAI Responses, and Anthropic Messages

routellm

A framework for serving and evaluating large language model routers.

routerllm

Smart LLM request router — route prompts to the right model based on cost, speed, quality or complexity

rsazure-openai-toolkit

A fast, modular, secure, and auditable toolkit to integrate with Azure OpenAI — with a friendly CLI and dev-first architecture.

rusticai-litellm

Rustic AI module leveraging LiteLLM for LLMs

rvq-vae-gpt

Yet another attempt at GPT in quantized latent space

rwu-llmconnector

Unified LLM connectors for OpenAI, Google Gemini, Ollama, and LM Studio.

sapapj-langchain-proxy

Connect langchain to SAP's AI proxy.

scalexi-llm

A comprehensive multi-provider LLM proxy library with unified interface

scalexi-llm-proxy
seekgpt

A Python client library for SeekGPT and other OpenAI-compatible LLM APIs.

sekha-llm-bridge

Universal LLM adapter service for Sekha AI - Multi-provider bridge supporting 100+ LLMs via LiteLLM

selectorllm

Add your description here

semantic-llm-cache

Semantic caching for LLM API calls - reduce costs with one decorator

send-2-llm

A flexible LLM provider switching library

serapeum-azure-openai

serapeum azure openai integration

serapeum-openai

serapeum openai integration

serverless-openai

A package for using Openai in serverless environment

sgllm-python

The Official Python Library For The SGLLM API.

sgptcoder-sdk

The official Python library for the sgptcoder API

shopee-llm-admin

A small example package

shopee-ums-llm

A small example package

sievellm

Smart AI router — filters requests to the right model, saving 40-80% on costs

sik-llms

Lightweight, easy, and consistent LLM-interface across providers and functionality.

simple-gpt2

Wrapper of the DeepAI GPT-2 text generation API.

simple-llm-api

A simple and easy-to-use LLM API Wrapper

simple-mistral

A simple async and sync Mistral API client

simple-openai-requests

Unify common OpenAI API requests use cases into a simple interface

simplified-united-llm

A streamlined, lightweight LLM client library for OpenRouter and Ollama providers with structured output generation

sinapsis-openai

sinapsis module to handle OpenAI modules for chat completion, image edition and creation, audio generation, among other tasks

sitellm

SiteLLM= LiteLLM + Chinese + Security

sitellm-proxy-extras

Additional files for the SiteLLM Proxy. Please visit the sitellm project !

skorplandgpt-enterprise

Package for SkorplandGPT Enterprise features

skorplandgpt-proxy-extras

Additional files for the SkorplandGPT Proxy. Reduces the size of the main skorplandgpt package.

slimllm

Zero-dependency LiteLLM-compatible facade for OpenAI, Anthropic, and OpenRouter

smart-llm-router

Provider-agnostic LLM router. Pick the cheapest capable model per prompt with rule-based scoring. Wraps LiteLLM for format conversion + streaming.

smartllm

A unified async Python wrapper for multiple LLM providers with OpenAI Response API and reasoning support

smolllm

A minimal Python library for interacting with various LLM providers

smriti-agent-cache

Semantic and exact caching for LLM calls — cut costs by catching duplicate and similar prompts.

sno-llmix

Cross-runtime LLM orchestration for Python, TypeScript, and Rust with L2 caching, retries, key rotation, and config-driven runtime control

solveit-llm-proxy

A proxy that wraps Solveit as an OpenAI-compatible LLM API

speakeasy-openai

Python Client SDK Generated by Speakeasy

speedy-openai

Async OpenAI client for fast and efficient API requests using AIOHTTP module.

srai-openai

A set of functions to better interact with openai.

stable-openai

StableOpenai is an enhanced framework for OpenAI, providing stable and efficient API request management. It allows the use of multiple API keys to increase request limits and ensures thread safety. The library features multi-key management, thread-safe operations for reliable requests in multi-threaded environments, and automatic fallback to alternate keys when API rate limits are reached. Ideal for developers looking to optimize interactions with OpenAI's services in robust, concurrent applications.

stache-ai-anthropic

Anthropic provider for Stache AI

stache-ai-bedrock

Bedrock provider for Stache AI

stache-ai-cohere

Cohere provider for Stache AI

stache-ai-openai

Openai provider for Stache AI

subllm

Route LLM API calls through subscription-authenticated coding agents (Claude Code, Codex, Gemini CLI)

superduper-anthropic

Superduper allows users to work with anthropic API models. The key integration is the integration of high-quality API-hosted LLM services.

superduper-cohere

Superduper allows users to work with cohere API models.

superduper-openai

Superduper allows users to work with openai API models.

swarmauri_keyproviders_mirrored

Mirrored key provider for Swarmauri

swiftllm-py

A blazing-fast universal LLM gateway — call OpenAI, Anthropic, Gemini, Mistral & Ollama through one unified API.

synapse-langchain

LangChain integration for the Synapse decentralized AI model marketplace. Wraps the Synapse orchestrator's /api/infer endpoint as a standard LangChain LLM.

More in Agent frameworks & infrastructure