Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 21 of 41

aibabyllmclient

llmserver_call

aichina-openai-wrapper

A wrapper for OpenAI utilities

aiclient-llm

A minimal, generic client for AI models (OpenAI, Anthropic, Google, xAI) with middleware support.

aiconfig-extension-gemini

An extension for using Gemini with aiconfig

aiconfig-extension-groq

An extension for using the Groq client wrapper with AIConfig.

aiconfig-extension-llama

Model Parser extension for Llama

aidial-adapter-anthropic

Package implementing adapter from DIAL Chat Completions API to Anthropic API

aigpt

Python βιβλιοθήκη για επικοινωνία με το OpenAI API μέσω requests

aijson-llm
aiobedrock

AWS boto3 bedrock client in async

aioclaude-api

An unofficial API for Claude AI, allowing users to access and interact with Claude AII

aiogpt

An asyncio wrapper for the OpenAI ChatGPT API

airbender-py-anthropic

Anthropic provider for Airbender Python SDK

airbender-py-openai

OpenAI provider for Airbender Python SDK

airlock-llm

Enterprise LLM proxy built on LiteLLM — logging, guardrails, and unified access for AI coding tools.

akgpt

A Python library for interacting with Pollinations.ai API with support for text, images, and audio processing.

alea-llm-client

ALEA LLM client abstraction library for Python

all-the-llms

A unified interface for querying Large Language Models (LLMs) across multiple providers using LiteLLM and OpenRouter

ally-ai-langchain

langchain-openai package for ally

ally-ai-llamaindex

llamaindex azure openai package for ally

anthropic-bridge

Bridge Anthropic API to OpenRouter and OpenAI models.

anthropic-compat

Drop-in replacement for the Anthropic SDK that silently handles Claude 4.6 breaking changes

anthropic-qpython

The official Python library for the anthropic API

any-llm-client

Add your description here

any-llm-platform-client

Decrypt provider API keys using X25519 sealed box encryption and challenge-response authentication

any-llm-sdk
anyllm

A thin, unified LLM abstraction layer. Call any LLM with a single API.

api-gpt4

The GPT-4 API is an interface for interacting with the powerful GPT-4 language model. It allows you to generate natural language text, perform question-answering tasks, and more. Whether you're building chatbots, content generators, or creative writing tools, GPT-4 has got you covered!

api2openai

Create a Python package.

apigptcloud

All in one AIGC API package for Python

apimyllama

A package for interacting with the APIMyLlama API

arcllm

Unified LLM abstraction layer for autonomous agents

arcllm-sdk

The arc connecting you to every LLM. Minimal dependencies, maximum performance.

arp-llm

Shared helper for calling LLM providers across the ARP/JARVIS stack.

ask-amazon-bedrock

A Python utility to query Amazon Bedrock

async-batch-llm

Renamed to llm-minder. Installs llm-minder and keeps `import async_batch_llm` working as an alias.

async-chatgpt-api

Async OpenAI API wrapper - [Incomplete]

async-claude-client

async client for claude.ai and slack.com

async-llm-handler

An asynchronous handler for multiple LLM APIs

async-openai

Unofficial Async Python client library for the OpenAI API

aura-llm

Python SDK for Aura LLM Gateway - Open Responses API

autobyteus-llm-client

Async Python client for Autobyteus LLM API

autogemini

AutoGemini - 流式Gemini API处理系统

autogen-gigachat

Gigachat client for autogen

autogen-oaiapi

An OpenAI-compatible API server for AutoGen.

autogen-openaiext-client

This is an autogen>=0.4 extension for integrating external models through the OpenAI API.

automix-llm

Library for Mixing Multiple Models with differential costs and performance.

avalAgent

AI agent wrapper for AvalAI API with retry and model fallback support

awesome-llm-wrapper

A unified wrapper for multiple LLM APIs including OpenAI, Gemini, and Anthropic

aws-bedrock-runtime-mate

Make the Amazon Bedrock Runtime API easier to use with intuitive Python interfaces and type-safe utilities.

aws-bedrock-token-generator

A lightweight library for generating short-term bearer tokens for AWS Bedrock API authentication

aws-bedrock-wrapper

Async Python wrapper for AWS Bedrock LLMs with caching, retries, and structured outputs

aws_crllm

Python client sdk of CR-LLM.

axio-transport-anthropic

Anthropic Claude transport for Axio (direct API and Vertex AI)

axio-transport-openai

OpenAI-compatible transport for Axio

axonflow-litellm

AxonFlow governance integration for LiteLLM

azllm

A Python package that provides an easier user interface for multiple LLM providers.

azure-llm-toolkit

Azure OpenAI client wrapper with rate limiting, cost tracking, and retry logic

azure-openai-blaster

High-throughput scheduler & resilience toolkit for Azure OpenAI endpoints (queueing, rate-limit smoothing, backoff, tracing).

azure-openai-limits

Static token limits for Azure OpenAI models (context/output), with CLI.

azureChatGPT

ChatGPT is a reverse engineering of Azure ChatGPT API

azureopenai
ba-openai

A version of the OpenAI package that allows the caching of responses, tailored for the CBS BA class.

basejump-llama-index-llms-azure-openai

llama-index llms azure openai integration

basejump-llama-index-llms-bedrock-converse

llama-index llms bedrock converse integration

basejump-llama-index-llms-openai

llama-index llms openai integration

basejump-llama-index-program-openai

llama-index program openai integration

basellm

One client to rule them all

basicbedrock

An abstraction layer for AWS Bedrock. Removes the need to keep track of response/request schemas.

batch-openai

A developer-friendly helper for OpenAI's Batch API

batch-stream-openai

Async batch runner for OpenAI API calls with streaming support

batched-chatgpt

Easy calling chatgpt with batched instances

batchedllm

like itertools.batched but for calling LLM

bedrock-anthropic

Client library for the anthropic API with the AWS Bedrock endpoint.

bedrock-converse

Python SDK for AWS Bedrock Converse API with tool calling, embeddings, and vector search

bedrock-gateway-client

Python client for AWS Bedrock Gateway with IAM authentication

bedrock-inference

Login into your AWS and call Bedrock models in Python

bedrock-kit

Small, opinionated AWS Bedrock client wrapper: adaptive throttle, cache-aware cost tracking, and structured-output parse-and-repair. Single-cloud, single-purpose.

bedrock-limiter-sdk

Drop-in replacement for boto3 bedrock-runtime client with token limiting

bedrock-ops

Production-grade boto3 toolkit for AWS Bedrock: typed retry, per-model timeouts, capability lookup, full token usage with cache fields, PII-safe Guardrails.

bedrock-region-balancer

AWS Bedrock region load balancer with round-robin distribution and batch processing

bedrockrouter

Python SDK and CLI for BedrockRouter — use every AWS Bedrock model through a self-hosted proxy with friendly aliases and cost tracking

bestehorn-llmmanager

A comprehensive Python library for managing AWS Bedrock Converse API interactions with multi-model support, intelligent retry logic, and parallel processing capabilities

blockrun-litellm

LiteLLM adapter for BlockRun — call 90+ AI models via LiteLLM with a BlockRun API key or an x402 USDC wallet (Solana or Base)

bodhiext.cohere

Bohilib plugin for Cohere by bodhiext

bodhiext.openai

Bodhilib plugin for OpenAI APIs

borgllm

Universal LLM client with API key rotation, rate limit management, and custom fallback strategies. Drop-in OpenAI SDK replacement with optional LangChain support.

botrun-litellm

A wrapper for litellm with TAIDE configuration support

bridgellm

Provider-agnostic LLM client with agentic capabilities. One interface, any provider.

bridgic-llms-openai

OpenAI adapters for Bridgic.

bridgic-llms-openai-like

OpenAI-like LLM adapters for Bridgic, enabling connectivity with external LLM providers.

buggpt

A free and open source API for accessing various large language models

bulkllm
bytedxllm-client

This is a reserved placeholder package to mitigate dependency confusion risks.

cached-llm
cached-openai

A version of the OpenAI package that allows the caching of responses

cachellm-py

Auto-optimize LLM prompt caching. Save 60-90% on Claude, GPT & Gemini API costs.

callllm

Asynchronous, concurrent requests to the LLM REST APIs.

callm-py

Keep callm and process thousands of requests without (rate) limits.

callme-gate

一个简单的低负载联网网关,提供HTTP请求路由和处理功能

More in Agent frameworks & infrastructure