Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 37 of 41

relmio

Turn a supported ChatGPT/Codex OAuth sign-in into a private OpenAI-compatible endpoint, starting with self-hosted n8n.

@benvargas/pi-openai-fast

OpenAI fast mode toggle for pi - Enables priority service tier on supported GPT-5 and GPT-6 models

@openai-oauth/ai-sdk

Vercel AI SDK provider adapter for openai-oauth auth handles.

@agentprodready/ai-provider-openai

OpenAI and OpenAI-compatible AI provider adapters for AgentProdReady (chat, tools, streaming, embeddings).

@oneciel-ai/ciel-runtime

Universal AI coding-agent runtime and model-routing layer for Claude, Codex, AGY, ZCode, and compatible runtimes.

@openai-oauth/local

Local Codex auth-file auth handle for openai-oauth.

@peler1nl1kelt0s/tokenflow

An open-source resource scheduler and traffic-shaping proxy for AI agents

@zgltyq/pi-provider-kimi-code

Kimi Code models in pi-coding-agent with OAuth, K3, K2.7, and HighSpeed selection

agent-cn

国内 Agent 工具一键接入国产模型:官方直连、零中转、全中文、可自检

ai-dynamo-llm

AI Dynamo LLM serving client — OpenAI-compatible inference client with multimodal support

bindai-provider-openai

OpenAI provider for BindAI

claude-code-openai

OpenAI-compatible API server for the Claude Code CLI — streaming, tools, vision, and live session reuse.

dbx-tools-litellm

LiteLLM Databricks provider with live endpoint discovery and fuzzy model resolution

gosce-authenticated-llm-jwt-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

llama-index-llms-trustedrouter

llama-index llms TrustedRouter integration

llm-failover-router

Resilient Multi-Provider LLM Fallback Router (DeepSeek, OpenAI, Ollama, Anthropic).

llm-microsoft-foundry

LLM plugin for Microsoft Foundry models, authenticated via Azure CLI

llm-provider-router

Lightweight provider router foundation.

llm-unity

Unified interface for interacting with multiple LLM providers.

needlepath-litellm

Needlepath context selection as a LiteLLM proxy CustomGuardrail.

nexus-llm

Official Python SDK for the Centralized LLM Platform

ollama-openttt

TTTPS Proof-of-Time reverse proxy for Ollama: cryptographic audit-trail timestamps for local model responses via the public KPP Provenance API

hiapi

HiAPI review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. One API for leading AI image, video, and text generation models.

@shiro-sdk/openai

OpenAI provider plugin for Shiro.

airroute

AirRoute — free AI gateway. One endpoint, many free providers, auto-fallback, adaptive auto routing, token compression, and a full admin console. Works with Claude Code, OpenCode, Cline, Copilot & any OpenAI/Anthropic-compatible agent.

adopt-agent

The single model seam: budget, tracing, idempotency, adapters. Implemented in S7.

aq-llm-pivot

A unified LLM wrapper for online APIs and local models

claude5

通过openai兼容的api代理运行claude code, 不修改claude code的配置

gosce-authenticated-mcp-agent-aed9d5

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

litellm-ucash

Bill LiteLLM LLM proxy calls via U.CASH pay-per-token. Non-custodial.

llm-1password

Resolve llm model API keys from 1Password op:// references

llm-provider-adapter

Provider-neutral synchronous chat adapters for OpenAI, Claude, DeepSeek, OpenRouter, and LiteLLM.

llm-router-utils

Lightweight extraction of sglang's reasoning/tool-call parsers and chat template rendering for router services.

llm-sidecar

Local sidecar giving any tool grounded, cited, routed AI — Ollama or OpenRouter, no API key required.

llmhotspot

Share an LLM API quota across devices on a local network (Wi-Fi hotspot, USB tether, or LAN)

@deepseek-ai/dsh-llm-retry

Provider-routed LLM request retry policy for the DeepSeek Harness

@deepseek-ai/dsh-llm

Provider-neutral LLM service interface for the DeepSeek Harness

write-language

Multi-provider language generation toolkit using Vercel AI SDK - generate responses with 10+ LLM providers including OpenAI, Anthropic, Google, and more.

@deepseek-ai/dsh-llm-pi-ai

pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)

@deepseek-ai/dsh-llm-deepseek

DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam

@saptarishi/cds-plugin-llm

LLM-agnostic AI platform for SAP CAP. 11 providers behind one API (Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Ollama, Groq, Fireworks, DeepSeek, Mistral, OpenAI-compatible, SAP Generative AI Hub) with 30+ middleware primitives spanning cost/resi

acp2api

OpenAI-compatible HTTP server over ACP agents. Use Claude Code, Codex, opencode or any ACP CLI from anything that speaks the OpenAI API but does not speak ACP yet.

@deepseek-ai/dsh-host-apiproxy

API gateway: the ApiProxy contract (api/), the fetch carrier pair (fetch/), and the host-side gateway plugin providing ctx.apiProxy

@xpert-ai/plugin-moonshot

## Overview

openzoo

Local x402-paying proxy + MCP server for openzoo.fun — point any OpenAI-compatible harness (Cursor, Claude Code, aider, SDKs) at localhost and it pays per call from a local burner wallet. Solana and Base rails live; Robinhood experimental. `openzoo build|

@chai-ai/openai

OpenAI provider for chai-ai.

@wienerberliner/pi-openai-fast

Minimal Pi extension for OpenAI Fast mode.

@rabbit-agent-sdk/provider-openai

This is the OpenAI provider for the Rabbit Agent SDK.

@monotykamary/pi-better-openai

Improve OpenAI in pi with fast mode, usage stats, realtime voice, image generation, and footer polish.

@matatbread/matbot-provider-openai-compat

OpenAI-compatible chat completions provider adapter (OpenAI and any compatible endpoint) with streaming and tool calls.

@purista/harness-openai

OpenAI model provider adapter for @purista/harness.

@llm-ports/adapter-openai

OpenAI SDK adapter for llm-ports. Implements LLMPort and EmbeddingsPort. baseURL support covers 10+ OpenAI-compatible providers (Azure, Groq, Together, Fireworks, DeepInfra, Perplexity, Cerebras, LiteLLM proxy).

@agentprodready/ai-provider

Provider-neutral AI contracts for AgentProdReady — execute, stream, tools, and embeddings without vendor lock-in at the boundary.

@depup/ai-sdk__anthropic

@ai-sdk/anthropic with all dependencies updated to latest

agentbridge-cli

Bridge OpenAI tools to Claude Code SDK, Codex CLI, and OpenRouter

agentgov-cli

TokenAllot CLI — wrap Claude Code, bind work items, check gateway health.

agentgov-gateway

TokenAllot FastAPI gateway (vaults ANTHROPIC_API_KEY; enforces from signed policy cache; §12.1)

agnos-proxy-llm-gateway

Agnos Proxy - the gateway-agnostic control plane for LLM routing, cost-tracking and observability. OpenAI-compatible governance proxy over a swappable BackendEngine.

kuafu-llm-sdk

LLM infrastructure layer with multi-provider fallback, health monitoring, speed probing, and alerting.

llm-velocity

llm_velocity is a lightweight framework designed to build high-performance, cost-effective AI agents. It drastically reduces LLM call expenses and accelerates response times by intelligently optimizing how the language model is utilized.

mom-llm

A Mixture-of-Models OpenAI/Anthropic-compatible LLM gateway that fans out to a panel of models and synthesizes one answer.

parakeet-index-llms-litellm

parakeet-index llms LiteLLM integration

xyberos-llm-providers

Remaining LLM providers plugin (RFC-0019, M6): OpenAI-compatible presets + Bedrock + Vertex, no new architecture

@zhivex-ai/azure-openai

Azure OpenAI adapter for Zhivex AI SDK.

@charivo/server

Server-side provider adapters for Charivo

@slopus/happy-providers

Stateful Node.js sessions for Codex, Claude, Grok, Bedrock, and Responses-compatible model providers.

@sap-ai-sdk/openai

SAP AI SDK integration with the official OpenAI npm package for Azure OpenAI on SAP AI Core

@launchdarkly/server-sdk-ai-openai

LaunchDarkly AI SDK OpenAI Provider for Server-Side JavaScript

@jmanuelcorral/openteam

Cost-aware, local-first routing plugin for opencode with cheapest-capable frontier fallback and multi-agent orchestration.

@agentic-kit/pi-ext-metered-model

pi extension that routes model calls through the Constructive metered gateway, so a pi session is metered exactly like agentic-server traffic

capo-bedrock

Typed, async Python SDK for AWS Bedrock.

dhivehigpt-sdk

Python SDK for the DhivehiGPT API

ffwf-tau-llm

τ-llm: Unified LLM provider abstraction (OpenAI-first)

gptproto

Spec-driven SDK for the gptproto async media generation API

infinity_agent

强类型、可扩展的 LLM 异步客户端库,支持 OpenAI 兼容 API、流式对话、工具调用与多模型消息格式

litellm-as-code

Declarative runtime-state management for a LiteLLM proxy: reconcile users/teams/keys/credentials/models from a YAML spec.

llm-rates

One vendored litellm-catalog snapshot + one public overlay + shared lookup/cost math for portfolio LLM pricing

llm-seam

Unified LLM abstraction with provider pattern for portfolio projects

llm-tiyuvta

Retired: the tiyuvta inference endpoint closed on 2026-09-28. Tiyuvta now builds AI integration for non-tech companies: https://tiyuvta.ai/

parakeet-index-llms-watsonx

parakeet-index llms watsonx integration

spakky-llm

Multi-provider LLM adapter plugin for Spakky Agent

vela-llm

Local LiteLLM proxy for GitHub Copilot models with OpenAI and Anthropic-compatible APIs.

@unieai/uad-llm

Provider-neutral LLM service interface for the DeepSeek Harness

langchain-llm7

LangChain integration for the LLM7 Chat API

@tomflow/proflow-agent-gateway

The sole Custom GPT Actions HTTP ingress and OpenAI transport anti-corruption layer.

pi-fireworks-provider

Fireworks AI provider extension for pi - Access Kimi, MiniMax, GLM, DeepSeek, and GPT-OSS models through the Fireworks AI API

@warlock.js/ai-groq

Groq adapter for @warlock.js/ai (OpenAI-compatible, thin wrapper over @warlock.js/ai-openai)

pi-clinepass-provider

ClinePass provider for pi — access GLM-5.2, Kimi K2.7, DeepSeek V4 and more open-weight coding models through Cline's $9.99/mo subscription

agent-model-router

零依赖的 OpenAI 兼容模型智能路由调度器

fastclaude

Small completions-style Python interface backed by the Claude CLI

gosce-ai-getvda-anthropic-google-auth-oauthlib-mc-aed9d5

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

llm-api-adapter-mistral

Official Mistral API package for llm-api-adapter

llm-router-gate

A CLI and SDK for routing LLM calls and gating according to price.

llmns

Parse, normalize, and compare llm:// references (llmns, a name system for language models)

subactor-subllm

Central provider, model and application routing policy for Subactor LLM consumers.

reapiai

reapi.ai review: compare features, pricing, use cases, access model, and alternatives for this Model Serving agent in 2026. A unified API platform for accessing multiple AI models

openarva

Enterprise Autonomous Multi-Model AI Agent Gateway Engine

focalapi-cli

让任意 AI Agent 直接调用 focalapi 创作模型的命令行工具

@neil9466/gpt-expert-mode

GPT 专家模式:让免费/低成本 LLM agent 调用 ChatGPT 网页版作为决策主脑,无需 API Key。基于 parley CDP 框架二次开发。Use ChatGPT (web) as the decision brain for low-cost LLM agents, no API key needed.

@monotykamary/dsh-llm

Provider-neutral LLM service interface for the DeepSeek Harness

More in Agent frameworks & infrastructure