Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 19 of 41

@tokenlens/models

Tree-shakeable static models.dev catalog split by provider for TokenLens.

@ai-sdk/openai-compatible

This package provides a foundation for implementing providers that expose an OpenAI-compatible API.

@earendil-works/pi-ai

Unified LLM API with automatic model discovery and provider configuration

routiform

Routiform — Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.

@ai-sdk/azure

The **[Azure provider](https://ai-sdk.dev/providers/ai-sdk-providers/azure)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Azure OpenAI API.

@openai/codex-responses-api-proxy

<p align="center"><code>npm i -g @openai/codex-responses-api-proxy</code> to install <code>codex-responses-api-proxy</code></p>

@robota-sdk/agent-provider-openai-compatible

OpenAI-compatible providers (DeepSeek, Qwen, Gemma) for Robota SDK

gpt-tokenizer

A pure JavaScript BPE tokenizer with model metadata and pricing for GPT-5, GPT-4o, o-series, and other OpenAI models

@metorial/openai-compatible

OpenAI-compatible provider base for Metorial. Provides common functionality for OpenAI-compatible API providers.

dual-brain

AI orchestration across Claude + OpenAI subscriptions — smart routing, budget awareness, and dual-brain collaboration

azure-openai

Node.js library for the Azure OpenAI API

@opeoginni/github-copilot-openai-compatible

GitHub Copilot API OpenAI-Compatible Provider for AI SDK

portkey-ai

Node client library for the Portkey API

genkitx-azure-openai

Genkit AI framework plugin for Azure OpenAI APIs.

@tokenlens/helpers

Helpers for context windows, usage normalization, compaction, and cost estimation.

openai-gpt-token-counter

Count the number of OpenAI tokens in a string. Supports all OpenAI Text models including GPT-5, GPT-4, GPT-3.5-turbo, and specialized models

@tinyclaw/plugin-provider-openai

OpenAI provider plugin for Tiny Claw

@tokenlens/fetch

Typed client for models.dev to fetch model catalogs with friendly errors.

@conclave-ai/agent-grok

Conclave AI Grok agent — OpenAI-wire-compatible, routes to xAI's api.x.ai/v1 with strict-JSON-schema structured output.

clasp-ai

Claude Language Agent Super Proxy - Translate Claude/Anthropic API calls to OpenAI-compatible endpoints

fastify-openai

OpenAI Fastify plugin

@adaline/openai

Adaline OpenAI

@vercel/ai-sdk-openai-websocket-fetch

WebSocket transport for the AI SDK OpenAI provider — drop-in fetch replacement that routes streaming requests through a persistent WebSocket connection.

@duheso/zerocli

Zero CLI to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

ollama-agent-router

Ollama agent router and local LLM router for OpenAI-compatible model routing, GPU-aware queues, async jobs, and CLI configuration.

@zerople/hermes-shim-http

Run Claude, Codex, or OpenCode as a local OpenAI-compatible HTTP provider for Hermes and other clients.

@ai-sdk/groq

The **[Groq provider](https://ai-sdk.dev/providers/ai-sdk-providers/groq)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Groq chat and completion APIs, transcription support, and browser search tool.

acptoapi

Anthropic SDK to multi-provider streaming bridge — converts Anthropic message format and tool calls to Gemini, OpenAI-compatible APIs

@oh-my-pi/pi-ai

Unified LLM API with automatic model discovery and provider configuration

@cherrystudio/ai-core

Cherry Studio AI Core - Unified AI Provider Interface Based on Vercel AI SDK

@helios-agent/pi-ai

Unified LLM API with automatic model discovery and provider configuration

openai-streams

Tools for working with OpenAI streams in Node.js and TypeScript.

@jeffreycao/copilot-api

GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.

openai-api

A tiny client module for the openAI API

@openplaw/openclash

ACP to OpenAI protocol conversion gateway - expose ACP agents as OpenAI-compatible API endpoints

@aeon-ai-pay/aigateway

AI Agents discover, invoke, and settle paid LLMs, APIs, and Skills — starting with Skill Boss. No manual key setup. No prepayment. Pay-per-call via x402 or Agent Card.

@blockrun/xclawrouter

Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.

@ai-sdk/gateway

The Gateway provider for the [AI SDK](https://ai-sdk.dev/docs) allows the use of a wide variety of AI models and providers.

@ai-sdk/anthropic

The **[Anthropic provider](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Anthropic Messages API](https://docs.anthropic.com/claude/reference/messages_post).

@ai-sdk/xai

The **[xAI Grok provider](https://ai-sdk.dev/providers/ai-sdk-providers/xai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the xAI chat and completion APIs.

@ai-sdk/amazon-bedrock

The **[Amazon Bedrock provider](https://ai-sdk.dev/providers/ai-sdk-providers/amazon-bedrock)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Amazon Bedrock [converse API](https://docs.aws.amazon.com/bedrock/latest/APIR

ai-sdk-provider-opencode-sdk

AI SDK v7 provider for OpenCode 2.x via @opencode/client: sessions, streaming, tool approvals, and interactive forms

@ai-sdk/mistral

The **[Mistral provider](https://ai-sdk.dev/providers/ai-sdk-providers/mistral)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model, embedding model, and speech model support for Mistral APIs.

@openrouter/ai-sdk-provider

![hero illustration](./assets/banner.png)

@ai-sdk/deepseek

The **[DeepSeek provider](https://ai-sdk.dev/providers/ai-sdk-providers/deepseek)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [DeepSeek](https://www.deepseek.com) platform.

@ai-sdk/google-vertex

The **[Google Vertex provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-vertex)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Google Vertex AI](https://cloud.google.com/vertex-ai) APIs.

@ai-sdk/cohere

The **[Cohere provider](https://ai-sdk.dev/providers/ai-sdk-providers/cohere)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Cohere API.

@ai-sdk/togetherai

The **[Together.ai provider](https://ai-sdk.dev/providers/ai-sdk-providers/togetherai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Together.ai](https://together.ai) platform.

@ai-sdk/cerebras

The **Cerebras provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for [Cerebras](https://cerebras.ai), offering high-speed AI model inference powered by Cerebras Wafer-Scale Engines and CS-3 systems.

@google/generative-ai

Google AI JavaScript SDK

@anthropic-ai/sdk

The official TypeScript library for the Anthropic API

@ai-sdk/fireworks

The **[Fireworks provider](https://ai-sdk.dev/providers/ai-sdk-providers/fireworks)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model and image model support for the [Fireworks](https://fireworks.ai) platform.

@ai-sdk/perplexity

The **[Perplexity provider](https://ai-sdk.dev/providers/ai-sdk-providers/perplexity)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for Perplexity's Sonar API - a powerful answer engine with real-time web search capabilities.

@google-cloud/vertexai

Vertex Generative AI client for Node.js

@ai-sdk/deepinfra

The **[DeepInfra provider](https://ai-sdk.dev/providers/ai-sdk-providers/deepinfra)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the DeepInfra API, giving you access to models like Llama 3, Mixtral, and other state-of-th

@firebase/ai

The Firebase AI SDK

@ibm-cloud/watsonx-ai

IBM watsonx.ai Node.js SDK

@anthropic-ai/vertex-sdk

The official TypeScript library for the Anthropic Vertex API

ai-gateway-provider

AI Gateway Provider for AI-SDK

@anthropic-ai/bedrock-sdk

The official TypeScript library for the Anthropic Bedrock API

@ai-sdk/baseten

The **[Baseten provider](https://ai-sdk.dev/providers/ai-sdk-providers/baseten)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model and embedding model support for the [Baseten](https://baseten.co) platform.

ai-retry

Retry and fallback mechanisms for AI SDK

ai-sdk-provider-gemini-cli

Community AI SDK provider for Google Gemini using the official CLI/SDK

@tanstack/ai-gemini

Google Gemini adapter for TanStack AI chat, images, speech, audio generation, and structured outputs.

dify-ai-provider

Dify provider for Vercel AI SDK

@mistralai/mistralai

TypeScript client library for the Mistral AI API

venice-ai-sdk-provider

Venice AI provider for the Vercel AI SDK

@gguf/claw

Multi-channel AI gateway with extensible messaging integrations

@ai-sdk/huggingface

The **[Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/index)** for the [Vercel AI SDK](https://ai-sdk.dev/docs) contains language model support for thousands of models through multiple inference providers via the Hugging

@aihubmix/ai-sdk-provider

<div align="center"> <a href="README.md">🇺🇸 English</a> | <a href="README.zh.md">🇨🇳 中文</a> | <a href="README.ja.md">🇯🇵 日本語</a> </div>

@firebase/vertexai-preview

A Firebase SDK for VertexAI (preview)

@mymediset/sap-ai-provider

SAP AI Core provider for AI SDK (powered by @sap-ai-sdk/orchestration)

@firebase/vertexai

A Firebase SDK for VertexAI

@ai-sdk/moonshotai

The **[Moonshot AI provider](https://ai-sdk.dev/providers/ai-sdk-providers/moonshotai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Moonshot AI](https://platform.moonshot.cn) platform, including the Kimi model serie

vercel-minimax-ai-provider

Vercel AI Provider for running MiniMax AI models

@llmgateway/ai-sdk-provider

Forked from https://github.com/OpenRouterTeam/ai-sdk-provider

zhipu-ai-provider

Vercel AI SDK Custom Provider for Services from Zhipu (Z.ai)

sealclaw

Multi-channel AI gateway with extensible messaging integrations

@anthropic-ai/foundry-sdk

The official TypeScript library for the Anthropic Foundry API

anthropic-vertex-ai

[nalaso/anthropic-vertex-ai](https://github.com/nalaso/anthropic-vertex-ai) is a community provider that uses Anthropic models through Vertex AI to provide language model support for the Vercel AI SDK.

@requesty/ai-sdk

![NPM Version](https://img.shields.io/npm/v/%40requesty%2Fai-sdk) ![NPM Downloads](https://img.shields.io/npm/dm/%40requesty%2Fai-sdk)

@tanstack/ai-openrouter

TanStack AI adapter for OpenRouter chat, provider tools, structured outputs, and access to hundreds of LLMs.

@cherrystudio/ai-sdk-provider

Cherry Studio AI SDK provider bundle with CherryIN routing.

rosetta-ai

The translation layer for LLM provider messages

@gaodefa/daocore

Multi-channel AI gateway with extensible messaging integrations

workers-ai-provider

Workers AI Provider for the vercel AI SDK

ai-fallback

Automatically switch AI SDK model provider when one of the providers has downtime

@quail-ai/azure-ai-provider

ai sdk compatible provider for azure(non OpenAI models)

@ai-sdk/open-responses

The **[Open Responses provider](https://ai-sdk.dev/providers/ai-sdk-providers/open-responses)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for [Open Responses](https://www.openresponses.org/) compatible APIs.

@0xmaxma/claude-gateway

Multi-agent gateway for Claude

@agentick/gateway

Standalone daemon for multi-client, multi-agent access

@starlink-awaken/agentmesh

Unified Agent Gateway - Multi-Agent Scheduler and Router

pi-xai

xAI / Grok extras for Pi — Grok Build protocol, Imagine tools, usage QoL, agentic APIs (provider transitional)

@sooneocean/agw

Agent Gateway — multi-agent task router for Claude, Codex, Gemini with combos, DAG, DSL

@nkbai/agent-gateway

Multi-agent orchestration gateway

@naveenkumarbaskaran/agent-gateway

Multi-agent orchestration gateway

seracade

Seracade is a drop-in OpenAI-compatible routing proxy for AI agent teams. Six named capabilities: Call (every request, addressable and replayable), Step (sub-Call routing context inside agent trajectories), Quality Score (calibrated, version-stamped quali

@tessera-llm/vercel-ai

Drop-in Tessera integration for the Vercel AI SDK. One line of config routes generateText / streamText / generateObject / streamObject through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/an

@tessera-llm/mastra

Drop-in Tessera integration for the Mastra agent framework. One line of config routes every Mastra Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/m

@satgate/sdk

Node.js SDK for SatGate Gateway and SatGate Cloud private-beta APIs

More in Agent frameworks & infrastructure