Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 23 of 41
Simple, unified interface for all major LLMs
A lightweight bridge that lets the Claude Code CLI authenticate and run through Databricks Foundation Models using Databricks OAuth.
Scalable multi-provider LLM library with unified interface for OpenAI, Gemini, Anthropic, Deepseek, Moonshot and xAI
Interface to handle multiple LLMs and AI tools.
A simple Python wrapper for OpenAI API without Pydantic dependencies
A lightweight, provider-neutral library for translating LLM requests and responses across model APIs.
A beautiful unified LLM interface for Django with persistence and streaming
Anthropic inference backend plugin for Docketeer
Unified LLM model implementations for Donkit (OpenAI, Azure OpenAI, Claude, Vertex AI, Ollama)
Base building blocks for DP OpenAI completion flows (callbacks, API base, DB connector).
Provider-agnostic single-query LLM client with PostgreSQL recording and catalog storage.
A small CLI that lets Claude Code reach non-Anthropic models — Ollama, Perplexity, OpenAI, Gemini — through a subagent that knows how to call it.
轻量级LLM API客户端库,支持缓存、重试和详细日志记录功能
DSPy integration for ChatGPT Codex subscription-backed language models
DSPy LM integration for Claude Code CLI - route DSPy requests through local Claude Code agent
Pi-style LM authentication helpers for DSPy
A Python client for DuckGPT
A flexible package for switching AI models during agent execution
Utilities for orchestrating OpenAI chat, tool calling, search, audio, and images from one helper package.
Easy GPT utils include 1. chat completion 2. embedding and 3. vector database
Easy '1-line' calling of every LLM from OpenAI, MS Azure, AWS Bedrock, GCP Vertex, and Ollama
Description
An easier way to query LLMs
Intelligent multi-model LLM router with auto-calibration and multilingual support
Drop-in LiteLLM replacement backed by Rust — same API, 10× lower latency
A lib for cached LLM calling and translation
Efficient Agent Router — routes tasks to the best LLM under quality, latency, cost, and safety constraints
Async client for OpenAI, Azure OpenAI, Microsoft Foundry, Google Gemini and TypeSafe decision models
A lib for cached LLM calling and translation
A caching utility for Elasticsearch leveraging vector search
elizaOS Anthropic Plugin - Claude API client for text and object generation
Groq LLM plugin for elizaOS - Python implementation for fast inference
elizaOS OpenAI Plugin - OpenAI API integration for text, image, audio, and embeddings
A plugin for Enthusiast that provides an OpenAI connector.
A plugin for Enthusiast that provides an Mistral connector.
A plugin for Enthusiast that provides an OpenAI connector.
Orchestration tool for managing third-party LLM API providers
Drop-in Anthropic SDK shim for EvalOps llm-gateway routing
Drop-in OpenAI SDK shim for EvalOps llm-gateway routing
Evolution OpenAI with automatic token management
LiteLLM provider for exoclaw
OpenAI-compatible LLM provider for exoclaw with streaming request bodies, per-model routing, and CPython + MicroPython support
Provider-agnostic LLM call_tool router with yaml routing, fallback chains, and cost telemetry.
LLM client for 'expert'
A wrapper library to abstract common llm providers
A more reasonable OpenAI API.
A Fake OpenAI API based on pandora
High-performance Rust acceleration for LiteLLM
FastAPI for Large Language Models
A composable FastAPI LLM gateway with unified multi-provider support
FastAPI router factory for OpenAI-compatible Chat Completions, Responses, and Files endpoints
Seamlessly integrate with top LLM APIs for speedy, robust, and scalable querying. Ideal for developers needing quick, reliable AI-powered responses.
Fast and easy wrapper around LLMs.
High-performance parallel LLM API request tool with caching and multiple provider support
OpenAI-based server for Fetchcraft
High-performance LLM client with batch processing, caching, and checkpoint recovery
FoundationaLLM Command-Line Tools
FLLM Command-Line Tools Core Module
Local-first LLM gateway with token usage analytics for AI developers
A blazing-fast gateway for asynchronous, high-concurrency LLM requests (OpenAI, Claude, etc.).
The official Python library for the flyflow API
llama-index llms anthropic integration
llama-index llms anyscale integration
llama-index llms azure openai integration
llama-index llms gemini integration
llama-index llms gradient integration
llama-index llms huggingface integration
llama-index llms openai integration
llama-index llms openai like integration
llama-index llms replicate integration
llama-index program openai integration
This package holds the ChatGPT plugins for flytekit
This package holds the openai plugins for flytekit
Anthropic Claude plugin for flyte
Google Gemini plugin for flyte
OpenAI plugin for flyte
A simple, unified interface for multiple LLM providers
ChatGPT is a reverse engineering of OpenAI's ChatGPT API
Free API-based LLM Cascading
Library for use free gpt 3.5 in python
A Python toolbox for easy interaction with various LLMs and Vision models
Use LLMs for Free.
Library for use free gpt 3.5 in python
freeGPT provides free access to text and image generation models.
free chatgpt api, not need token
Chain multiple free-tier LLM APIs with automatic rate limit fallback
Library for interacting with multiple AI APIs
FreeGPTHub: A truly free, unified GPT API gateway—unlike “fake-free” alternatives that hide paywalls behind quotas, trials, or mandatory top-ups.
The project provides free access to ChatGPT-4, GPT-4o-mini, and SearchGPT models for integration into Python applications.
The simplest Python client for free access to top-tier AI models (GPT-4.1 Nano, DeepSeek, Gemini Flash, Claude Haiku)
A unified API interface for Groq and Google's Gemini AI models
A user-friendly wrapper for the Google Gemini 2.0 API
A Python package for the Gemini AI generative model
A robust, lightweight Python wrapper for the Google Gemini API.
A helper library for integrating the Google Gemini API into web applications.