Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 20 of 41

@tunnlo/bridge-llm

Direct LLM API bridge for Tunnlo (Anthropic, OpenAI, Ollama)

brainstormrouter

BrainstormRouter TypeScript SDK — AI gateway with memory, guardrails, and governance

adaptive-memory-multi-model-router

Best in class open source LLM router across 47+ providers with Evolution-inspired routing: EXP3 diversity, MVT rate-limit rotation, optimal defense theory verification.

tmlpd-pi

Run N LLMs in parallel, keep the best answer. Confidence-scored ensemble merging beats sequential fallback on latency and quality. 40-60% token savings built in.

@gatewards/agent-sdk

Pipeline gateway client for multi-agent systems — drop-in proxy, budget enforcement, dedup cache (optional x402 settlement)

@axiom-lattice/gateway

API Gateway for LangGraph agent-based applications

AI-ChatGPT-Free

免费的ChatGPT Python库

ASUllmAPI

A simple python package to facilitate connection to ASU LLM API

AllLLMs

A wrapper for various large language models including GPT, Claude, and Gemini

BatchGPT

A package for handling ChatGPT prompt for large datasets

ChatGPT-Cloud

A package for Pandora-ChatGPT

ChatGPT-lite

ChatGPT is a reverse engineering of OpenAI's ChatGPT API

ChatGPT2API

ChatGPT is a copy from ChatGPT2API

ChatGptLibWrapper

A simple ChatGPT wrapper

ClaudeAI-api

A Python package provides an unofficial api for interacting with the Claude from Anthropic

CustomGPT

A package for interacting with GPT-4 models (and older) without using the OpenAI API.

EasyAPIOpenAI

Python classes for interacting with OpenAI's API to use ChatGPT or DALL-E very easily.

ErisPulse-OpenAI

ErisPulse OpenAI 通用接口封装模块

GPT-Helper

A helper library for interacting with ChatGPT.

GPT-Simple

an easier to use version of the OpenAI library

GPT-wrapper

ChatGPT is a reverse engineering of OpenAI's ChatGPT API

GPTConnect

A python package to make GPT functions easy

GPTIntegration

A module for integrating various GPT models for diverse tasks.

GPTInterface

A simple interface to OpenAI's GPT-3 API.

GPTManager

Package for managing GPT API access

GPTRouter

A Python package for working with GPTRouter APIs

GeminiRequests

Gemini AI module (using Gemini AI API through requests lib)

GlobleXGPTAi

GlobleXGPTAi Model Python Client (Multi-Provider Support) developed by Himanshu

Gpt4Zero

Gpt4Zero - python библиотека для бесплатного взаимодействия с передовыми нейросетями.

GptCode

ChatGpt API接口的封装

GroqAuto

Drop-in async Groq client with automatic API key rotation on rate limits

HalaGPT

Library for interacting with multiple AI APIs

LBGPT

Load balancer for asynchroneous requests to the APIs of OpenAI and Azure (if configured) for ChatGPT

LLM-Bridge

A library that wraps multiple LLM providers into a consistent API while using each provider's native SDK internally, supporting multimodal I/O, file processing, and stream output.

LLM-Mediator

Just a simple mediator for different LLM models.

LLMRateLimiter

Rate limiter for LLM

LineAuthGPT

An unofficial Python wrapper for OpenAI's ChatGPT API

LlaMasterKey

One master key for all LLM/GenAI endpoints

MistralGPTIntegration

Integration utility for Mistral AI API to provide GPT-based functionalities.

MyLLM

A python package to interact with llm model supported by g4f and langchain.

Myself-openai1

access a selfopenai

OneLLMAPI

A package that integrates the APIs of multiple major language model manufacturers.

OpenAIAuth

OpenAI Authentication Reverse Engineered

OpenChatGPT

A Python package for integrating with the internal OpenAI Chat API.

OpenaiBatchAPI

OpenaiBatchAPI: A Python Library that supports OpenAI Batch API

PickYourLLM

Pick Your LLM: Intelligent, Use-Case Aware LLM Model advisor for Optimal Performance and Cost

PurGPT.py

PurGPT.py, the wrapper for the PurGPT API

PyGptRes

PyGptRes is a Python module for interacting with OpenAI's GPT-3.5 Turbo API to create natural language conversations with cutting-edge language models.

SwiftLLM

A python package to access most common foundation models easily.

USTB-OpenAI

OpenAI style API for accessing the USTB hosted LLM

UnlimitedChatGPTWebAPI

Unlimited ChatGPT WebAPI

UnlimitedGPT

An unofficial Python wrapper for OpenAI's ChatGPT API

WrappedLLM

A wrapper for various large language models including GPT, Claude, and Gemini

YaGPT

This Python library provides a simple wrapper for interacting with Yandex Language Models, making it easy to send requests for text generation.

abf-openai

A version of the OpenAI package that allows the caching of responses, tailored for the CBSxWallStreetPrep 'AI in Business and Finance' class.

abstractllm

A unified interface for large language models with support for OpenAI, Anthropic, Hugging Face, Ollama, and MLX

actllminfer

Integrated LLM inference engine with a LangChain-Core-style interface across Kimi, GLM, MiniMax, DeepSeek, OpenAI, Anthropic, Hugging Face, and NVIDIA NIM.

aeroai-mistral

Mistral AI integration for AeroAI

aeroai-openai

OpenAI integration for AeroAI

agent-budget-guard

Budget-limited LLM API client wrapper to prevent runaway AI agent costs

agent-delegate

Universal cheap-subagent CLI — route low-reasoning tasks from Claude Code / Codex to Ollama, LM Studio, OpenRouter, Anthropic Haiku, and other backends.

agent-delegator

Agent-agnostic AI CLI delegation with federated model failover

agent-grid-protocol

Agent Grid Protocol SDK - Autonomous AI API Quota & Token Exchange Client

agent-grid-protocol-core

Agent Grid Protocol SDK - Autonomous AI API Quota & Token Exchange Client

agent-registry-router

Registry-driven LLM routing: build classifier prompts from agent descriptions, validate decisions, and dispatch.

agent-response-transformer

A Python SDK to transform Claude response to OpenAI response format

agent-toolbox

Standardized Agent Runtime — preset-based AI agent gateway with stable HTTP API

agentcache

Official Python client for AgentCache.ai - Reduce LLM costs by 90%

agentcc

Python SDK for the AgentCC LLM Gateway — OpenAI-compatible, type-safe, with guardrails and observability

agentclear-fallback

Never let your AI agent fail again — automatic fallback to AgentClear's marketplace of 60+ API services.

agentforge-bedrock

AWS Bedrock provider for AgentForge — Anthropic, Titan, Cohere on Bedrock

agentforge-litellm

LiteLLM router-based LLM provider for AgentForge — 100+ underlying providers through one interface

agentforge-openai

OpenAI LLM + embeddings provider for AgentForge — gpt-4o / o-series + text-embedding-3-*

agentfuse-runtime

Intelligent LLM agent cost optimization runtime — per-run budget enforcement, semantic caching, model routing across 15 providers

agentgateway

A centralized framework to use a model of your choice for your agentic usecases.

agenthub-python

AgentHub is the LLM API Hub for the Agent era, built for high-precision autonomous agents.

agentic-ai-gateway

Production-grade LLM gateway with cost tracking, budget alerts, conversation memory, streaming, guardrails (PII/injection defense), Redis caching, and multi-provider routing

agentic-api

Agentic API gateway for OpenAI-compatible inference servers

agentic-gateway

Universal agent protocol gateway — translate between A2A, MCP, OpenAI Assistants, and REST in one config file.

agentic-llm-gateway

LLM gateway with payments for agentic workflows and applications

agentic-router

Agentic LLM router for classification and decision making.

agentica-gateway

Agentica Gateway: FastAPI server, Web UI, IM channels and cron for the agentica agent runtime

agentkeyswitch

Cross-platform CLI for switching Claude and Codex API profiles.

agentnet

ModelCaller for AI

agentopt-py

Find the right LLM models for your AI agents — automatic model selection with accuracy/cost/latency tradeoffs

agentpick

AgentPick — The runtime layer for agent tools. One API, every tool, AI routing, auto-fallback.

agentready-sdk

Cut your AI token costs by 40-60%. Drop-in proxy for OpenAI, LangChain, LlamaIndex, CrewAI.

agentrelay-cli

OpenAI- and Anthropic-compatible API server that routes through agent CLIs

agentsiq

Intelligent Multi-Model Router for LLM Selection

agentspend-sdk

AgentSpend — runtime cost optimizer for AI agents. Route LLM calls to the cheapest capable model with fallbacks, loop guards, and telemetry.

agentsuite-sdk

VirtueAI Agent Suite SDK — Gateway for AI agents

agentwrap

Wrap agents, ship APIs - Turn agent CLIs into libraries and OpenAI-compatible servers

aglet-builtin-model-litellm

Aglet ModelProvider that routes to 100+ LLMs via the LiteLLM SDK.

aglet-builtin-model-openai

Aglet ModelProvider that talks to any OpenAI-compatible chat-completions endpoint.

ai-agent-gateway

Generic AI agent gateway with MCP tool support and streaming

ai-agent-gateway-cli

Canonical dev CLI client for ai-agent-gateway

ai-agent-proxy

Mailbox-backed AI agent proxy server

ai-llama-module

Simple and lightweight Python wrapper for Llama AI API

ai-llm-router

Intelligent routing of LLM API calls across multiple providers with automatic fallbacks, cost optimization, and monitoring

aibaba_ai_openai

An integration package connecting OpenAI and Aibaba AI

More in Agent frameworks & infrastructure