Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 33 of 41
Official Python SDK for TajikGPT API — chat, images, and video generation
TechVLLM.AI Python package for Groq-based LLM integration.
ChatGPT is a reverse engineering of OpenAI's ChatGPT API
Drop-in Tessera integration for AutoGen (autogen_core / autogen_agentchat / autogen_ext). One line of config routes your AutoGen agents' LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings.
Drop-in Tessera integration for CrewAI. One line of config routes your CrewAI agents' LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings.
Drop-in Tessera integration for LangChain. One line of config routes your existing ChatOpenAI / ChatAnthropic / ChatMistralAI / ChatGroq / ChatCohere through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy.
Drop-in Tessera integration for LlamaIndex. One line of config routes your existing OpenAI / Anthropic / Mistral / Groq / Cohere LLM through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy.
Tessera SDK — drop-in LLM cost optimization. One line patches OpenAI, Anthropic, Mistral, Groq, Cohere clients to route through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free tier: 60M tokens/mo. Production: 20% of measured savings, $0 if none.
Drop-in Tessera integration for Pydantic AI. One line of config routes your Pydantic AI Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings.
Python SDK for ThaiLLM API
The official gpt4free repository | various collection of powerful language models
Concurrent Fast OpenAI calls with Automatic Rate Limiting to avoid hitting limits. Structured Outputs with Pydantic Base Models.
Smart LLM routing with TIBET provenance - route queries to Ollama/OpenAI/Anthropic automatically
Cycle Anthropic OAuth keys with master API-key fallback.
Tiny OpenAI ChatGPT and Whisper API Library
Official sync and async Python SDK for the OpenAI-compatible TitanGPT API
A lightweight library for generating short-term bearer tokens for AWS External Anthropic API authentication
Intelligent LLM task planner — decompose tasks, route to optimal models, enforce budgets
Набор простеньких инструментов для собственного openai-совместимого эндпоинта.
Some simple utils packaging OpenAI util.
An extension for tracdap-runtime that lets models connect to OpenAI endpoints
TRACER: Trace-Based Adaptive Cost-Efficient Routing. Turn LLM traces into parity-gated routing policies - cut 90%+ of LLM calls with formal guarantees.
A flexible LLM manager that shifts between multiple models
LLM Gateway with Anthropic-compatible API
An LLM API proxy that improves response quality through concurrent inference, pivot-tournament verification, and context refinement.
turbo agent auth manage tool, to support adjust auth
A python based wrapper for GPT-4 & GPT-3.5 PLUS.
A python based wrapper for GPT-4 & GPT-3.5 PLUS.
A fully typed, validated async client for the Gemini API
An easy to use API and CLI wrapper for chatGPT and other AIGC API base on utype
LangChain-compatible chat models and embeddings for UiPath's LLM services
UiPath LLM Client
A unified interface for local Large Language Model(LLM) models and online LLM providers.
Placeholder
Pre-compromise fork of litellm - Library to easily interface with LLM API providers
A unified async client for interacting with multiple LLM providers
Unified chat() interface for multiple LLM providers (OpenAI, Anthropic, Gemini).
A unified interface for calling various Large Language Model APIs
Unified Python client for multiple LLM providers (OpenAI, Anthropic, etc.) with drop-in compatibility.
Unified Large Language Model Interface for ChatGPT, LLaMA, Mistral, Claude, and RAG
A Python library for unified access to all kinds of large language models.
A streamlined, lightweight LLM client library for OpenRouter and Ollama providers with structured output generation
Support for Unity Catalog functions as LiteLLM tools
Minimal universal LLM client - swap providers with one env var
Библиотека для работы с языковыми моделями
Universal interface for different LLM providers
An unofficial Formosa Foundation Model API client implementation compatible with LangChain and OpenAI
Minimalistic library to call OpenAI API, with httpx and type-hinting
A reverse engineered API for the Vercel AI playground.
A Python library for interacting with the VersaCore LLM Chat API.
VersaLLM is a versatile language model client that supports multiple backend models including OpenAI, Anthropic, and Groq. It provides a unified interface for interacting with these models and includes tools for executing functions based on user prompts.
Anthropic integration for Vespwood
OpenAI integration for Vespwood
A Python package for vgemini
Lightweight local LLM proxy with multiple provider management, automatic failover, privacy protection, and latency-based selection.
A Python package for interacting with OpenAI-compatible LLMs
OpenRouter plugin for vision agents
A unified interface for efficient LLM inference with vLLM and OpenAI-compatible APIs
High-performance Rust-based load balancer for VLLM with multiple routing algorithms and prefill-decode disaggregation support
vLLM Semantic Router - Intelligent routing for Mixture-of-Models
Virtual Ollama: Wrap any OpenAI-compatible API into an Ollama-compatible API.
A lightweight client for local LLM APIs like Ollama or OpenWebUI
A lightweight, model-agnostic LLM provider abstraction with streaming and tool support
Standalone llm adapter/routing layer with a demo UI for testing provider connections and call and output signature comparison.
Universal LLM interfaces for multi-provider chat and utilities
Haystack integration for WhichModel — cost-aware LLM model selection
A unified LLM model version and capability management library
OpenAI integration for the Wildcard ecosystem.
An litellm wrapper.
Wrap custom generate function as an OpenAI SDK compatible API service.
OpenAI-Compatible Proxy Middleware for the Wyoming Protocol
OpenAI-compatible API Gateway with Anthropic support and token package sales
A Python library for accessing various free AI providers, inspired by g4f.
A client library for making requests to various LLMs through a unified interface
alpha version of YandexGPT package for Python.
Библиотека для работы с Yandex GPT API с поддержкой синхронного и асинхронного режимов, реализацией потоковой генерации текста и возможностью распознавания речи с определением говорящего
A package to prevent Dependency Confusion attacks against Yandex.
Module for simple connecting to YandexGPT Api
A Python SDK for interacting with the YandexGPT API.
Получение ответов от YandexGPT Lite
Unified streaming LLM interface with provider-agnostic reasoning/tool-call abstraction
有赞 LLM 统一调用库
A zen, simple, and unified API to prompt LLMs from Anthropic, Google, OpenAI, and more, using only the requests library.
OpenAI-compatible Chat Completions provider for Zeno (OpenAI, OpenRouter, LiteLLM, Azure v1, Ollama, vLLM).
OpenAI-compatible utilities for Zeroshot Python packages.
Run prompts against LLMs hosted by Moonshot
A unified gateway to manage, debug, and analyze your AI models.
Authentication provider for Cursor, extracting credentials from local environment or agent.
Turn GitHub Copilot into an OpenAI/Anthropic-compatible server with Claude Code and Codex support.
Multi-channel AI gateway with extensible messaging integrations
AWS credential provider that sources credentials from known environment variables
Fast, minimal Node.js wrapper for the Voids API AI chat completions.
A blazing fast local proxy server that caches LLM API calls to save costs during development.
Lightweight API key proxy for llama.cpp server with token usage tracking
Use your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, the Agent SDK, your scripts — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint.