Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 24 of 41
Gemini Batch API utility
A Python module to process bulk data using Google's generative AI (Gemini).
A helper library for AI text generation using Google Gemini API.
A Fastapi Based Proxy for Gemini API
OpenAI-compatible API wrapper for Gemini CLI
Unofficial Gemini API with Firefox cookie auto-retrieval and easy chat client.
Smart Gemini API key manager with token-aware sliding window scheduling
Global CMD Gemini LLM
A package to rotate Gemini API models based on rate limits.
Next-generation Gemini API Client
Simplified Sequential Processor for Google Gemini API
Parallel Gemini API calls with MongoDB logging support
⚠️ This package is no longer maintained. No future updates will be released.
A python client for the Gemini API and Websocket
Modules for working with Gemini's API in a pythonic way
Gemini API reimplementation
A lightweight Python library for Google Gemini API key rotation and model fallback.
Key rotator, don't get dizzy.
API client for Gemini
Library for generating consistent Gemini API outputs and wrapping them with json and python objects
x
OpenAI provider adapters for genblaze (Sora, DALL-E, TTS)
A unified, provider-agnostic Python client for multiple LLM APIs
Genie Flow Invoker Ollama
Genie Flow Invoker OpenAI on Azure
Deprecated: This package has been renamed to genkit-anthropic.
Lightweight LLM routing layer over native provider SDKs
LLM plugin for Glueco Gateway SDK - Typed chat completions for OpenAI, Groq, Gemini
Quick call to openai chatgpt api web page
A package for interacting with the Gemini model
A Python client library for the Goliath LLM API
OpenAI client with Gonka network integration
Decentralized GPT API for everyone !
Python client sdk to access GPT's AI-powered conversational functionality (without OpenAI API key nor VPN)
A package for batch processing with OpenAI API.
Efficiently and robustly use the OpenAI Batch API in Python
Tools for splitting jobs across multiple OpenAI batches
Minimal OpenAI GPT client for Python - chat, embeddings, functions, streaming, no heavy deps
Client for GPT-Gateway.com including ChatGPT Retreiver Plugins
Tools for setup/communications to a LLM models
Trims the messages array for ChatGPT API
Wrapper for the GPT2 Api
Утилита для проксирования OpenAI, Anthropic и Gemini запросов в GigaChat
Wrapper for GPT3 API
Module for working with GPT-3 API by Roughs Team
A trivial command line tool to invoke OpenAI's completion API
gpt4 api engine
Default template for PDM package
Python package for unofficial GPT-4 API access via chat.openai.com using Chrome browser via Selenium
The official gpt4free repository | various collection of powerful language models
This package simplifies your interaction with various GPT models, removing the need for tokens or other methods to access GPT
OpenAI & Ollama compatible API powered by your ChatGPT account
A python based wrapper for GPT-4 & GPT-3.5 PLUS.
统一的LLM调用库,支持多种LLM提供商、文件上传、环境感知
Add your description here
Add your description here
The official Python library for the groq API
Drop-in async Groq client with automatic API key rotation on rate limits
A Python client for the GROQA API
The official Python library for the groq API
Use Groq.com as llm
A Python package.
Library to easily interface with LLM API providers
Strict JSON LLM outputs with multi-provider support (Anthropic / OpenAI / DeepSeek / Kimi / Google)
Library to easily interface with LLM API providers
A Python SDK for Heroku's Managed Inference API (MIA), providing easy access to AI models through a LangChain-compatible interface.
A comprehensive Python wrapper for Large Language Models with database integration and usage tracking
A comprehensive Python wrapper for Large Language Models with database integration and usage tracking
HiWay2LLM SDK (Python) — OpenAI-compatible client for the HiWay router. BYOK, 40-60% savings, 0% markup on inference.
Hopeit Agents: LLM models client
A unified interface for multiple LLM providers with caching and interactive development mode to get massive cost savings.
Drop-in OpenAI client for the Morpheus decentralized inference network (mor.org)
LLM cost compression through intelligent RAG and multi-tier routing
Official Python SDK for the iGPT API
LLM integration for BFAgent Hub ecosystem — DB-driven routing, LiteLLM backend, resilient adapters (ADR-089)
use any llm api in a plug-and-play fashion
A toolkit for initializing LLMs and embeddings with multiple providers
Intercept OpenAI inputs
Inscode GPT API python package
sageLLM Gateway - OpenAI/Anthropic compatible API Gateway (L6)
LiteLLM integration for PandasAI
Jentic Apitools LLM - Unified LLM utilities and provider abstraction for consistent LLM usage across packages
Client for JsonLLM API
Jupyter AI module that provides a ChatGPT model engine.
A JupyterLab extension that provides LiteLLM model abstraction
Production-focused Python library for multi-provider LLM management with unified API
Retab official python library
OpenAI API wrapper
Minimal LLM client getter for OpenAI Responses + OpenAI-compatible Chat Completions.
Thin, provider-native LLM client for direct model calls within the KAOS ecosystem
Kodemeio LiteLLM CLI — manage LiteLLM proxy instances
Reference keel-llm-protocol adapter for Anthropic's Messages API — the divergent-provider grounding for the standard.
Reference keel-llm-protocol adapter for AWS Bedrock — enterprise gateway. Use Claude / Llama / Titan / Mistral / Cohere models hosted on Bedrock with the Keel vendor-neutral protocol + reliability + OTel stack.
Reference keel-llm-protocol adapter for Google's native Gemini generateContent API.
Reference keel-llm-protocol adapter for any OpenAI-compatible chat endpoint (OpenAI, Groq, OpenRouter, Mistral, vLLM, Ollama, ...).
Composed reliability for multi-model LLM calls — quorum fan-out + primary/failover, category-dispatched, transparent degradation. Built on keel-llm-protocol + keel-circuit-breaker.
AWS Bedrock LLM provider plugin for Kestrel Sovereign.