Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 20 of 41
Direct LLM API bridge for Tunnlo (Anthropic, OpenAI, Ollama)
BrainstormRouter TypeScript SDK — AI gateway with memory, guardrails, and governance
Best in class open source LLM router across 47+ providers with Evolution-inspired routing: EXP3 diversity, MVT rate-limit rotation, optimal defense theory verification.
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.
Pipeline gateway client for multi-agent systems — drop-in proxy, budget enforcement, dedup cache (optional x402 settlement)
API Gateway for LangGraph agent-based applications
免费的ChatGPT Python库
A simple python package to facilitate connection to ASU LLM API
A wrapper for various large language models including GPT, Claude, and Gemini
A package for handling ChatGPT prompt for large datasets
A package for Pandora-ChatGPT
ChatGPT is a reverse engineering of OpenAI's ChatGPT API
ChatGPT is a copy from ChatGPT2API
A simple ChatGPT wrapper
A Python package provides an unofficial api for interacting with the Claude from Anthropic
A package for interacting with GPT-4 models (and older) without using the OpenAI API.
Python classes for interacting with OpenAI's API to use ChatGPT or DALL-E very easily.
ErisPulse OpenAI 通用接口封装模块
A helper library for interacting with ChatGPT.
an easier to use version of the OpenAI library
ChatGPT is a reverse engineering of OpenAI's ChatGPT API
A python package to make GPT functions easy
A module for integrating various GPT models for diverse tasks.
A simple interface to OpenAI's GPT-3 API.
Package for managing GPT API access
A Python package for working with GPTRouter APIs
Gemini AI module (using Gemini AI API through requests lib)
GlobleXGPTAi Model Python Client (Multi-Provider Support) developed by Himanshu
Gpt4Zero - python библиотека для бесплатного взаимодействия с передовыми нейросетями.
ChatGpt API接口的封装
Drop-in async Groq client with automatic API key rotation on rate limits
Library for interacting with multiple AI APIs
Load balancer for asynchroneous requests to the APIs of OpenAI and Azure (if configured) for ChatGPT
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.
Just a simple mediator for different LLM models.
Rate limiter for LLM
An unofficial Python wrapper for OpenAI's ChatGPT API
One master key for all LLM/GenAI endpoints
Integration utility for Mistral AI API to provide GPT-based functionalities.
A python package to interact with llm model supported by g4f and langchain.
access a selfopenai
A package that integrates the APIs of multiple major language model manufacturers.
OpenAI Authentication Reverse Engineered
A Python package for integrating with the internal OpenAI Chat API.
OpenaiBatchAPI: A Python Library that supports OpenAI Batch API
Pick Your LLM: Intelligent, Use-Case Aware LLM Model advisor for Optimal Performance and Cost
PurGPT.py, the wrapper for the PurGPT API
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.
A python package to access most common foundation models easily.
OpenAI style API for accessing the USTB hosted LLM
Unlimited ChatGPT WebAPI
An unofficial Python wrapper for OpenAI's ChatGPT API
A wrapper for various large language models including GPT, Claude, and Gemini
This Python library provides a simple wrapper for interacting with Yandex Language Models, making it easy to send requests for text generation.
A version of the OpenAI package that allows the caching of responses, tailored for the CBSxWallStreetPrep 'AI in Business and Finance' class.
A unified interface for large language models with support for OpenAI, Anthropic, Hugging Face, Ollama, and MLX
Integrated LLM inference engine with a LangChain-Core-style interface across Kimi, GLM, MiniMax, DeepSeek, OpenAI, Anthropic, Hugging Face, and NVIDIA NIM.
Mistral AI integration for AeroAI
OpenAI integration for AeroAI
Budget-limited LLM API client wrapper to prevent runaway AI agent costs
Universal cheap-subagent CLI — route low-reasoning tasks from Claude Code / Codex to Ollama, LM Studio, OpenRouter, Anthropic Haiku, and other backends.
Agent-agnostic AI CLI delegation with federated model failover
Agent Grid Protocol SDK - Autonomous AI API Quota & Token Exchange Client
Agent Grid Protocol SDK - Autonomous AI API Quota & Token Exchange Client
Registry-driven LLM routing: build classifier prompts from agent descriptions, validate decisions, and dispatch.
A Python SDK to transform Claude response to OpenAI response format
Standardized Agent Runtime — preset-based AI agent gateway with stable HTTP API
Official Python client for AgentCache.ai - Reduce LLM costs by 90%
Python SDK for the AgentCC LLM Gateway — OpenAI-compatible, type-safe, with guardrails and observability
Never let your AI agent fail again — automatic fallback to AgentClear's marketplace of 60+ API services.
AWS Bedrock provider for AgentForge — Anthropic, Titan, Cohere on Bedrock
LiteLLM router-based LLM provider for AgentForge — 100+ underlying providers through one interface
OpenAI LLM + embeddings provider for AgentForge — gpt-4o / o-series + text-embedding-3-*
Intelligent LLM agent cost optimization runtime — per-run budget enforcement, semantic caching, model routing across 15 providers
A centralized framework to use a model of your choice for your agentic usecases.
AgentHub is the LLM API Hub for the Agent era, built for high-precision autonomous agents.
Production-grade LLM gateway with cost tracking, budget alerts, conversation memory, streaming, guardrails (PII/injection defense), Redis caching, and multi-provider routing
Agentic API gateway for OpenAI-compatible inference servers
Universal agent protocol gateway — translate between A2A, MCP, OpenAI Assistants, and REST in one config file.
LLM gateway with payments for agentic workflows and applications
Agentic LLM router for classification and decision making.
Agentica Gateway: FastAPI server, Web UI, IM channels and cron for the agentica agent runtime
Cross-platform CLI for switching Claude and Codex API profiles.
ModelCaller for AI
Find the right LLM models for your AI agents — automatic model selection with accuracy/cost/latency tradeoffs
AgentPick — The runtime layer for agent tools. One API, every tool, AI routing, auto-fallback.
Cut your AI token costs by 40-60%. Drop-in proxy for OpenAI, LangChain, LlamaIndex, CrewAI.
OpenAI- and Anthropic-compatible API server that routes through agent CLIs
Intelligent Multi-Model Router for LLM Selection
AgentSpend — runtime cost optimizer for AI agents. Route LLM calls to the cheapest capable model with fallbacks, loop guards, and telemetry.
VirtueAI Agent Suite SDK — Gateway for AI agents
Wrap agents, ship APIs - Turn agent CLIs into libraries and OpenAI-compatible servers
Aglet ModelProvider that routes to 100+ LLMs via the LiteLLM SDK.
Aglet ModelProvider that talks to any OpenAI-compatible chat-completions endpoint.
Generic AI agent gateway with MCP tool support and streaming
Canonical dev CLI client for ai-agent-gateway
Mailbox-backed AI agent proxy server
Simple and lightweight Python wrapper for Llama AI API
Intelligent routing of LLM API calls across multiple providers with automatic fallbacks, cost optimization, and monitoring
An integration package connecting OpenAI and Aibaba AI