Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 33 of 41

tajikgpt

Official Python SDK for TajikGPT API — chat, images, and video generation

techvllm-ai

TechVLLM.AI Python package for Groq-based LLM integration.

tesla-revChatGPT

ChatGPT is a reverse engineering of OpenAI's ChatGPT API

tessera-autogen

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.

tessera-crewai

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.

tessera-langchain

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.

tessera-llamaindex

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-llm-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.

tessera-pydantic-ai

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.

thaillm-py

Python SDK for ThaiLLM API

theosgpt

The official gpt4free repository | various collection of powerful language models

throttle-openai

Concurrent Fast OpenAI calls with Automatic Rate Limiting to avoid hitting limits. Structured Outputs with Pydantic Base Models.

tibet-llm-router

Smart LLM routing with TIBET provenance - route queries to Ollama/OpenAI/Anthropic automatically

tiny-anthropic
tiny-claude-recycler

Cycle Anthropic OAuth keys with master API-key fallback.

tinyOpenAI

Tiny OpenAI ChatGPT and Whisper API Library

tinygent-anthropic
tinygent-mistralai
tinygent-openai
titangpt

Official sync and async Python SDK for the OpenAI-compatible TitanGPT API

token-generator-for-aws-external-anthropic

A lightweight library for generating short-term bearer tokens for AWS External Anthropic API authentication

tokenwise-llm

Intelligent LLM task planner — decompose tasks, route to optimal models, enforce budgets

tool2openai

Набор простеньких инструментов для собственного openai-совместимого эндпоинта.

tq-openai-utils

Some simple utils packaging OpenAI util.

tracdap-ext-openai

An extension for tracdap-runtime that lets models connect to OpenAI endpoints

tracer-llm

TRACER: Trace-Based Adaptive Cost-Efficient Routing. Turn LLM traces into parity-gated routing policies - cut 90%+ of LLM calls with formal guarantees.

tshift-llm

A flexible LLM manager that shifts between multiple models

ttllm-gateway

LLM Gateway with Anthropic-compatible API

turbo-agent

An LLM API proxy that improves response quality through concurrent inference, pivot-tournament verification, and context refinement.

turbo-agent-auth

turbo agent auth manage tool, to support adjust auth

turbogpt

A python based wrapper for GPT-4 & GPT-3.5 PLUS.

turbogpt-pro

A python based wrapper for GPT-4 & GPT-3.5 PLUS.

typed-gemini

A fully typed, validated async client for the Gemini API

uGPT

An easy to use API and CLI wrapper for chatGPT and other AIGC API base on utype

uipath-langchain-client

LangChain-compatible chat models and embeddings for UiPath's LLM services

uipath-llm-client

UiPath LLM Client

ullm

A unified interface for local Large Language Model(LLM) models and online LLM providers.

unblockedGPT

Placeholder

unclecode-litellm

Pre-compromise fork of litellm - Library to easily interface with LLM API providers

unified-llm-client

A unified async client for interacting with multiple LLM providers

unifiedllm-sdk

Unified chat() interface for multiple LLM providers (OpenAI, Anthropic, Gemini).

unify-llm

A unified interface for calling various Large Language Model APIs

unifyllm-sdk

Unified Python client for multiple LLM providers (OpenAI, Anthropic, etc.) with drop-in compatibility.

unillm

Unified Large Language Model Interface for ChatGPT, LLaMA, Mistral, Claude, and RAG

unionllm

A Python library for unified access to all kinds of large language models.

united-llm

A streamlined, lightweight LLM client library for OpenRouter and Ollama providers with structured output generation

unitycatalog-litellm

Support for Unity Catalog functions as LiteLLM tools

universal-llm

Minimal universal LLM client - swap providers with one env var

universal-llm-service

Библиотека для работы с языковыми моделями

univllm

Universal interface for different LLM providers

unofficial-ffm-openai

An unofficial Formosa Foundation Model API client implementation compatible with LangChain and OpenAI

uopenai

Minimalistic library to call OpenAI API, with httpx and type-hinting

vercel-llm-api

A reverse engineered API for the Vercel AI playground.

versacorellmchatapi

A Python library for interacting with the VersaCore LLM Chat API.

versallm

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.

vespwood-anthropic

Anthropic integration for Vespwood

vespwood-openai

OpenAI integration for Vespwood

vgemini

A Python package for vgemini

vibellm

Lightweight local LLM proxy with multiple provider management, automatic failover, privacy protection, and latency-based selection.

vinehoollm

A Python package for interacting with OpenAI-compatible LLMs

vision-agents-plugins-openrouter

OpenRouter plugin for vision agents

vllm-efficient-client

A unified interface for efficient LLM inference with vLLM and OpenAI-compatible APIs

vllm-router

High-performance Rust-based load balancer for VLLM with multiple routing algorithms and prefill-decode disaggregation support

vllm-sr

vLLM Semantic Router - Intelligent routing for Mixture-of-Models

vollama

Virtual Ollama: Wrap any OpenAI-compatible API into an Ollama-compatible API.

volt-llm-client

A lightweight client for local LLM APIs like Ollama or OpenWebUI

voxagent

A lightweight, model-agnostic LLM provider abstraction with streaming and tool support

vrraj-llm-adapter

Standalone llm adapter/routing layer with a demo UI for testing provider connections and call and output signature comparison.

vv-llm

Universal LLM interfaces for multi-provider chat and utilities

whichmodel-haystack

Haystack integration for WhichModel — cost-aware LLM model selection

whosellm

A unified LLM model version and capability management library

wildcard-openai

OpenAI integration for the Wildcard ecosystem.

wlitellms

An litellm wrapper.

wrap-openai

Wrap custom generate function as an OpenAI SDK compatible API service.

wyoming-openai

OpenAI-Compatible Proxy Middleware for the Wyoming Protocol

x-llmapi

OpenAI-compatible API Gateway with Anthropic support and token package sales

xgpt

A Python library for accessing various free AI providers, inspired by g4f.

xlitellm

A client library for making requests to various LLMs through a unified interface

yagpt-py

alpha version of YandexGPT package for Python.

yandex-gpt-api

Библиотека для работы с Yandex GPT API с поддержкой синхронного и асинхронного режимов, реализацией потоковой генерации текста и возможностью распознавания речи с определением говорящего

yandex-taxidwh-gptransfer-client

A package to prevent Dependency Confusion attacks against Yandex.

yandex_gpt

Module for simple connecting to YandexGPT Api

yandexgpt-python

A Python SDK for interacting with the YandexGPT API.

yandexgptlite

Получение ответов от YandexGPT Lite

yuullm

Unified streaming LLM interface with provider-agnostic reasoning/tool-call abstraction

yz-openai

有赞 LLM 统一调用库

zenllm

A zen, simple, and unified API to prompt LLMs from Anthropic, Google, OpenAI, and more, using only the requests library.

zeno-provider-openai

OpenAI-compatible Chat Completions provider for Zeno (OpenAI, OpenRouter, LiteLLM, Azure v1, Ollama, vLLM).

zeroshot-openai-utils

OpenAI-compatible utilities for Zeroshot Python packages.

zhipuai-langchain
zopyx.llm-moonshot

Run prompts against LLMs hosted by Moonshot

Helicone

A unified gateway to manage, debug, and analyze your AI models.

opencode-cursor-auth

Authentication provider for Cursor, extracting credentials from local environment or agent.

@jer-y/copilot-proxy

Turn GitHub Copilot into an OpenAI/Anthropic-compatible server with Claude Code and Codex support.

@pixelzx/genesis

Multi-channel AI gateway with extensible messaging integrations

@aws-sdk/credential-provider-env

AWS credential provider that sources credentials from known environment variables

unlimited-ai

Fast, minimal Node.js wrapper for the Voids API AI chat completions.

@dinakars777/cache-llm

A blazing fast local proxy server that caches LLM API calls to save costs during development.

smol-llm-proxy

Lightweight API key proxy for llama.cpp server with token usage tracking

@askalf/dario

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.

More in Agent frameworks & infrastructure