Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 35 of 41

gosce-authenticated-llm-agent

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

gosce-authenticated-multi-llm-agent

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

gosce-authenticated-mcp-agent

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

@tangle-network/tcloud

TypeScript SDK and CLI for Tangle Router, Sandbox, model routing, and agent service calls

gosce-authenticated-multi-llm-agent

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

justllm

Production LLM calls. Just the three lines. Reliability, native caching, and reversible context compression on by default.

proxyagent

Run any agent (Claude, Codex, custom) on any machine — with no API key on the machine. A secure, self-hosted proxy for models and tools.

subagent-fleet

Local AI compute control plane for Claude Code and coding agents. Route subagents across your Macs, GPUs, and Ollama nodes — with real-time fleet health, role-based routing, model warmup, and execution tracing.

@claudiolabs/claudin

Claudin — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, and 200+ models)

@ai-sdk/anthropic-aws

The **[Claude Platform on AWS provider](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic-aws)** for the [AI SDK](https://ai-sdk.dev/docs) gives you access to the Anthropic Messages API hosted in AWS at `aws-external-anthropic.{region}.api.aws`, aut

opencode-provider-tabnine

OpenCode plugin that exposes Tabnine Agentic as a provider

autourgos-openaichat

Autourgos LLM wrapper for the OpenAI Chat Completions API

ai-sdk-heal

Heal broken Vercel AI SDK message arrays before they hit the provider. Fixes orphaned tool calls, missing reasoning signatures, invalid tool names, and other provider rejections.

agentctx

kubectx-like CLI for switching Codex auth profiles

autogen-jarvisclaw

AutoGen (AG2) model client for JarvisClaw AI API (x402 USDC payments supported)

crewai-jarvisclaw

CrewAI LLM integration for JarvisClaw AI API (x402 USDC payments supported)

gpt-codex-client

OpenAI SDK-style Python client for ChatGPT/Codex OAuth-backed Responses workflows.

langchain-jarvisclaw

LangChain integration for JarvisClaw AI API (x402 USDC payments supported)

@nexus-cortex/cli

Nexus Cortex CLI - Terminal interface for multi-provider LLM orchestration

@juliusbrussee/caveman-ai

Unified LLM API with automatic model discovery and provider configuration

litellm-rvs

Library to easily interface with LLM API providers

llm-abstraction

Async LLM backend abstraction with Retry-After aware clients.

llm-spendguard

A pre-spend GATE + learning advisor for LLM API cost: caps every call, prices from a verified table, and learns the cheapest config that keeps quality.

@qode-agent/qprovs

Qode — LLM provider abstraction layer (Anthropic, OpenAI, Google, Ollama, etc.)

@vly-ai/integrations

Access AI models, email services, and project thumbnail capture through vly.ai and freebuff.com without managing multiple API keys or accounts

@makaio/adapter-openai-node

OpenAI adapter using the official OpenAI Node SDK for agentic chat completions.

xrouter-llm

Prompt-aware LLM routing-decision service: predicts which model can complete a prompt and picks the cheapest one.

@cgaravitoq/open-langchain-ts

Native LangChain BaseChatModel adapters for the Claude Code OAuth subscription (Anthropic) and opencode/Zen — no Pi, no API key.

llm-localfirst

Local-first LLM router: keep sensitive data and bulk text labor on your own models, call the cloud only for the hard part. Privacy-routing (fail-closed) + manager-worker delegation + allowlist guard, MCP-native.

llm7-quick

Быстрый доступ к LLM через api.llm7.io без API-ключа

@rex0220/llm-task-router

Thin, file-based CLI that routes a multi-step article workflow (brief → outline → draft → review → final) across OpenAI and Anthropic with fallback, schema validation, judge-model evaluation, and platform profiles (Qiita/Zenn/blog/note).

@nanio/registry

Model provider routers and fallback registry mechanisms for Nanio agentic framework (v0.0.1-alpha.4)

agent-provider-manager

Centralized API provider management for AI coding agents

gosce-authenticated-llm-agent

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

gosce-authenticated-mcp-agent

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

llmux-sdk

Scriptable LLM multiplexer — unified interface to Claude and OpenAI via subscription OAuth

local-llm-server

ローカルLLM(mlx / mlx-vlm / llama.cpp / vLLM / SGLang)を OpenAI 互換 API で束ねるマルチモデルゲートウェイ(サーバー)。gateway.toml のカタログを 1 ポートで配信し、model で振り分け・遅延起動・LRU 退避・MTP 高速化(Ollama 流の共有デーモン)。接続用クライアントは別パッケージ local-llm-client。

safe-openai-streaming

Fault-tolerant streaming wrapper for the official OpenAI Python SDK.

@mono-agent/openai-api-adapter

OpenAI-compatible Chat Completions adapter for host responders.

chatgpt-web-adapter

Local Python SDK and CLI bridge for authenticated consumer AI web products and hosted capabilities.

local-llm-client

ローカル LLM ゲートウェイ(local-llm-server / OpenAI 互換)に繋ぐ高レベルクライアント。エージェント共通のクライアントで、openai のボイラープレートを再実装しない(chat・画像・動画・音声認識/STT)。

orcarouter-haystack

Haystack integration for orcarouter

@ai-setu/client

AI Setu client — drop-in OpenAI SDK with workspace credit accounting and multi-provider routing.

@anyr/ai-sdk-provider

The AnyRouter provider for the Vercel AI SDK — call every AnyRouter model through `createAnyRouter`.

agentsave-inferroute

AgentSave InferRoute — PPD append-prefill routing sidecar for vLLM / SGLang (Enterprise)

axemere-gateway-anthropic

Axemere AI Gateway Anthropic SDK wrapper — drop-in Anthropic/AsyncAnthropic subclasses

axemere-gateway-langchain

Axemere AI Gateway LangChain integration — ChatAiGateway BaseChatModel

axemere-gateway-openai

Axemere AI Gateway OpenAI SDK wrapper — drop-in OpenAI/AzureOpenAI subclasses

fastllm-claude-code

Claude Code API for fastllm

gaard-llm

LLM provider adapters for GAARD

llm-gonkabroker

LLM plugin for Gonka Broker - OpenAI-compatible access to open-source models on the decentralized Gonka network

simpleopenai-proxy

Transparent OpenAI Chat Completions proxy and response normalizer

trimprompt

TrimPrompt — Save 80% on LLM tokens. Zero-config CLI proxy for AI coding agents

@kkmila/cpc

Custom Provider CLI for managing model providers

@apicity/openai

OpenAI / GPT provider for chat completions.

ai-sdk-local-fetch

Use Vercel AI SDK streamText directly on the client — no server required

@oasisomniverse/web6-api

Isomorphic (Node + browser) JavaScript/TypeScript client for the WEB6 OASIS AI Layer API v3.0 — 17 modules, 47 operations covering: unified AI completion across 99 providers (OpenAI, Anthropic, Gemini, Grok, Mistral, SambaNova, OpenRouter, Together AI, Pe

acp-openai-gateway

Expose any Agent Client Protocol (ACP) agent behind an OpenAI-compatible /v1 API

aether-ai-agent-cli

Aether Core AI v110 — Universal AI Gateway CLI (Python Wrapper)

batchllm-ai

Batch processing for LLM APIs - CSV/JSONL in, processed out. With retries, rate limiting, and cost tracking.

claude-model-router

Cost-aware model routing for the Claude API — reference implementation with a Claude Code subagent hook

gosce-authenticated-llm-oauth-agent

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

gosce-authenticated-mcp-agent-bcrypt

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

gosce-authenticated-mcp-traced-agent

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

jsmithpkp-llm-client-kit

Cached LLM client with Ollama + Anthropic provider dispatch, fixture mode, and JSON-schema-strict completions.

langchain-xynq

LangChain integration for XYNQ — decentralized OpenAI-compatible inference.

lfx-openai-compatible

Generic OpenAI-compatible endpoints (OpenRouter, Together, Groq, self-hosted vLLM/TGI, ...) as a first-class Langflow model provider, packaged as a standalone Extension Bundle.

lighthouse-llm-registry

A global reusable LLM Registry wrapper for LangChain models with unified error mapping for Lighthouse Agents Factory

llm-catalog-core

Gateway-agnostic core for llm-catalog: config schema, resolver, GatewayTransport, and LiteLLM codegen. Knows nothing about any runtime adapter.

llm-catalog-litellm

LiteLLM CustomLLM plugin for llm-catalog: drive a catalog config through LiteLLM, in-process or via the proxy.

llm-catalog-pydantic-ai

Pydantic AI adapter for llm-catalog: build native Pydantic AI models from a catalog config, routed through your gateway.

llm-market

Open clearinghouse for LLM bids, councils, and evidence-backed routing.

llmkit-cli

Run any LLM with one config file. No framework lock-in.

omnicall-llm-caller

Unified multi-provider LLM caller with automatic fallback

somm-langchain

LangChain BaseChatModel adapter for somm — lets LangChain/LangGraph/deepagents apps use somm as their LLM substrate

sovereign-rag-gateway

Policy-first OpenAI-compatible gateway for regulated workloads

switchboard-llm

A smart, OpenAI-compatible LLM router — a tiny triage-verify-escalate agent that saves cost without losing quality.

undercover-agent

An OpenAI-compatible chat completions server that logs harness traffic (dumb or MITM).

@reaatech/agent-budget-llm-router-plugin

LLM Router integration plugin for agent-budget-controller

zevairouter

ZevaiRouter - AI Router with provider automation, multi-account workflows, and quota tracking

@lite-agent/provider

Model providers for lite-agent: Anthropic Messages API + OpenAI Chat Completions (also OpenAI-compatible / local endpoints).

@caupulican/pi-ai

Unified LLM API with automatic model discovery and provider configuration

@plasius/ai-providers

Provider adapter contracts and implementations for the Plasius agentic AI package family.

gosce-authenticated-llm-mcp-agent

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

chatgpt-login

Login to ChatGPT with email:password, get access token + cookies

gosce-authenticated-mcp-jwt-agent

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

waken-azure-openai

Azure OpenAI Target adapter for Waken — routes waken Events to an Azure-hosted OpenAI deployment.

waken-bedrock

AWS Bedrock Target adapter for Waken — routes waken Events to any Bedrock-hosted model via the Converse API.

waken-claude

Claude Target adapter for Waken — routes waken Events to the Claude Agent SDK.

waken-cohere

Cohere Target adapter for Waken — routes waken Events to Cohere's chat API.

waken-gemini

Gemini Target adapter for Waken — routes waken Events to Google's google-genai SDK.

waken-groq

Groq Target adapter for Waken — routes waken Events to Groq's fast inference API.

waken-mistral

Mistral Target adapter for Waken — routes waken Events to Mistral AI's chat API.

waken-openai

OpenAI Target adapter for Waken — routes waken Events to the OpenAI Responses API.

apexapi

ApexApi review: compare features, pricing, use cases, access model, and alternatives for this Model Serving agent in 2026. One API key for 120+ AI models plus live web data. OpenAI-compatible.

@musistudio/claude-code-router

Local Claude Code Router gateway with CLI and web management UI.

@runtypelabs/mixlayer-ai-provider

AI SDK (Vercel) provider for Mixlayer — open-weight text and vision model inference over an OpenAI-compatible endpoint.

caesura-io-openai

Transparent wrapper for the OpenAI Python SDK to inject CaesuraO recommendations.

langchain-concentrate

LangChain integration for Concentrate.ai — a unified LLM gateway with the OpenAI Responses API.

noiton

🐙 Universal AI Agent Connector - one key, many agents (OpenCode, Hermes)

More in Agent frameworks & infrastructure