Agent frameworks & infrastructure

LLM gateways & API proxies

4,018 agents · most starred first

LLM gateways & API proxies, page 38 of 41

@unieai/uad-llm-retry

Provider-routed LLM request retry policy for the DeepSeek Harness

@veryfront/ext-llm-google

Veryfront first-party extension package for ext-llm-google

@monotykamary/dsh-llm-retry

Provider-routed LLM request retry policy for the DeepSeek Harness

@gosce/ai-getvda-bcrypt-langchain-core-mcp-d0e0d0

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.

@gosce/ai-getvda-bcrypt-langchain-core-mcp-dc2f7b

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

@gosce/ai-getvda-bcrypt-cryptography-langchain-cor-027cf2

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

@leanroute/langchain

LangChain integration for Leanroute. Drop-in `ChatLeanroute` chat model — same interface as `ChatOpenAI`, but routes across 14 LLM providers (OpenAI, Anthropic, Google, DeepSeek, Groq, xAI, and more) with cost caps, failover, and MCP support baked in.

@arcforge/engines

Provider connections for the Axon agent runtime — Anthropic, OpenAI, Google, Groq, Ollama and more.

@verlon-ai/sdk

TypeScript SDK for Verlon AI — the managed AI infrastructure platform that routes requests across LLM providers, evaluates response quality, runs experiments against live traffic, and auto-tunes routing configurations. Agent integration protocol: https://

@depup/openai

The official TypeScript library for the OpenAI API (with updated dependencies)

@fdekit/provider-openai

OpenAI provider adapter for FDEKit

@utdk/openai

Generated UTDK provider client for OpenAI API. The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.

@nestjs-agentic/openai

OpenAI-compatible ModelAdapter for nestjs-agentic. Works with OpenAI and any Chat Completions compatible endpoint such as Azure OpenAI, Ollama, vLLM, Groq, Together, OpenRouter, and LM Studio.

dsh-agentic-router

DeepSeek Harness plugin: learning agentic router — rule + UCB + LinUCB + k-NN experts under an EXP3 meta-selector, with a durable quality-reward flywheel, REAL model switching via the session request-header precedence chain, and STEP-LEVEL routing (v1.5.0

agentic-llm-router

Cost-aware multi-provider LLM router with role tiers (cheap/mid/chief/audit).

gemini-api-rotator

Production-grade Gemini API key rotation with cooldown, exponential backoff, RPM tracking, and persistent stats.

gosce-ai-getvda-bcrypt-cryptography-langchain-cor-027cf2

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

gosce-ai-getvda-bcrypt-langchain-core-mcp-d0e0d0

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

gosce-ai-getvda-bcrypt-langchain-core-mcp-dc2f7b

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

korullm

Policy-aware LLM routing, transports and drive strategies extracted from Koru.

langchain-openzoo

LangChain integration for OpenZoo - OpenAI-compatible inference with no signup

llm-api-adapter-xai

Official xAI Responses API package for llm-api-adapter

llm-batch-runner

Concurrent, caching, retrying OpenAI-compatible batch chat-completion runner with structured output validation.

llm-budget-proxy

A local proxy circuit breaker to stop runaway AI agents from burning API budgets.

llm-cheap-filter

Deterministic pre-filter + cheap→chief escalation pipeline — send only the few items that matter to your expensive model.

llm-openzoo

LLM plugin for models hosted by OpenZoo - no signup required

openai-codex-auth

Use the Codex CLI's ChatGPT login (~/.codex/auth.json) as a bearer credential for the Codex backend

purrcept_litellm

LiteLLM provider backend for purrcept_core.

resilient-llm-gateway

High-throughput LLM Gateway and Circuit Breaker for distributed AI agents

semora-llm

OpenAI-compatible chat model for Semora: official openai SDK, LangChain chunks.

smart-router-llm

Proxy inteligente entre APIs compatíveis com OpenAI e múltiplos provedores de LLM, com roteamento por complexidade e compressão de contexto.

universal-llm-connector

A unified interface to all major LLM providers with system certificate and async support

waldur-site-agent-litellm

LiteLLM (virtual key lifecycle + usage reporting) plugin for Waldur Site Agent

agent-translate-router

Standalone cross-provider translation router for AI-agent hooks with ordered fallbacks and shared caches

@veryfront/ext-llm-anthropic

Veryfront first-party extension package for ext-llm-anthropic

@m1khal3v/dsh-llm-key-rotation

Seamless API-key rotation for DeepSeek Harness LLM providers when subscription limits are hit

kangarouter

Evidence-driven multi-agent routing with deterministic safety gates.

claude-lite-llm

This is an LLM wrapper for claude and its subscription to use via Programming

claude-spillway

Quota-aware failover proxy for Claude Code: spills over from Anthropic to Ollama Cloud when your quota runs low, and switches back once it recovers.

llm-anthropic-general

Register Anthropic-protocol-compatible providers as first-class llm models

llm-hubris

LLM plugin for models hosted by Hubris

nucleusiq-openai-compatible

Generic OpenAI-compatible inference provider for the NucleusIQ AI agent framework (vLLM, SGLang, TGI, llama.cpp, LM Studio, NIM, and OpenAI-compatible clouds).

purra-anthropic

Official Anthropic Messages SDK adapter for PurrA

purra-openai

Official OpenAI Responses and Chat Completions SDK adapter for PurrA

pypaya-llm-client

One client for every OpenAI-compatible LLM server - local (Ollama, LM Studio, vLLM, llama.cpp) or hosted (OpenRouter, OpenAI) - with images and audio as plain message parts.

@deepseek-ai/dsh-plugin-package-inventory-deepseek

Active Loader-backed plugin package inventory for official DeepSeek LLM API requests

@gosce/authenticated-llm-agent-cryptography

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

@openclaw/ai

Reusable model provider adapters and streaming runtime from OpenClaw

dsh-codex-connect

ChatGPT OAuth and Codex models for DeepSeek Harness.

@asm-agent/ai

Unified LLM API with automatic model discovery and provider configuration

@wangmingfa/model-gate

LLM API 中转网关:配置文件配置多家运营商模型,对外暴露统一 OpenAI 兼容接口

@ai-sdk/zai

The Z.AI provider for the AI SDK contains language model support for Z.AI's GLM models.

@agentic-auto-correct/adapter-openai

OpenAI adapter for agentic-auto-correct.

@agentic-auto-correct/adapter-anthropic

Anthropic Claude adapter for agentic-auto-correct.

ai-parrot-client-groq

Groq LLM client for AI-Parrot (parrot.clients.groq)

ai-parrot-client-vllm

vLLM (OpenAI-compatible) LLM client for AI-Parrot (parrot.clients.vllm)

athena-llm

Athena LLM client — one seam across frontier, hosted-open (with failover), and local backends

claudex-export

Renamed to claudexer -- see https://pypi.org/project/claudexer/

combycode-llm-sdk

Unified LLM client for every major provider - one API, spec-driven wire format, real cost tracking.

conduit-llm

Conduit — lightweight AI driver for OpenAI-compatible, Ollama, Anthropic, Gemini (Python)

dexl-agents

One API. Every AI. Pay per call. Python client for DexL Agents.

durallm

Durable, self-healing multi-provider LLM gateway and circuit breaker with autonomous failover, tool idempotency, and context compaction for AI agents (Claude Code, Hermes, OpenClaw, OpenCode).

gosce-google-sign-in-claude-agent

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

llmclient-lite
purrcept-litellm

LiteLLM provider backend for purrcept_core.

radlab-llm-router

LLM Router – core library with optional API and metrics

vllm-algenta

Point vLLM (or any OpenAI-client-based consumer) at Algenta's own OpenAI-compatible /v1/chat/completions and /v1/responses surface -- a thin base-url/api-key helper plus a real, honest capability-fidelity conformance suite

@alvin0/ai-agent-sdk-provider-openai

Universal OpenAI adapter and provider plugin for ai-agent-sdk

@alvin0/ai-agent-sdk-provider-anthropic

Universal Anthropic adapter and provider plugin for ai-agent-sdk

@alvin0/ai-agent-sdk-provider-gemini

Universal Gemini Interactions adapter and provider plugin for ai-agent-sdk

@alvin0/ai-agent-sdk-protocol-gemini-interactions

Universal Gemini Interactions wire schema, serializer, and SSE translator for ai-agent-sdk

@alvin0/ai-agent-sdk-provider-http

Universal fetch, SSE, configurable provider, and provider-attempt accounting for ai-agent-sdk

@alvin0/ai-agent-sdk-protocol-anthropic-messages

Universal Anthropic Messages wire schema, serializer, translator, and dialect for ai-agent-sdk

@alvin0/ai-agent-sdk-protocol-responses

Universal OpenAI Responses and Codex wire schema, serializer, translator, and dialect for ai-agent-sdk

@alvin0/ai-agent-sdk-provider-codex

Universal Codex adapter, OAuth, injected auth contracts, and provider plugin for ai-agent-sdk

@deepseek-ai/dsh-deepseek-llm-api-extensions

Additive request-field registry for the official DeepSeek LLM API adapter

@dsh-enhanced/llm-route-capabilities

Runtime-local LLM route tool-call projection metadata for DeepSeek Harness integrations.

@pnpm/network.proxy-agent

Creates an http/s/socks proxy agent

@gosce/encrypted-oauth-llm-agent

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

@gosce/google-oauth-langchain-agent

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

@gosce/traced-openai-langchain-agent

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

@gosce/google-sign-in-langchain-agent

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

@assemblyline-agents/openai-codex

Pi-native OpenAI Codex subscription model provider plugin for Assembly Line.

@gosce/oauth-langchain-openai-agent

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

mohdel

Self-hosted LLM gateway and SDK for Node — a LiteLLM-style unified API for 16 providers (Anthropic, OpenAI, Gemini, Mistral, Groq, xAI, DeepSeek, OpenRouter, …) with per-call USD cost tracking, streaming, tool calls, vision, speech-to-text, and built-in O

aki-pro-max

Local-first OpenAI-compatible gateway and control plane for an authorized Postman web session.

myapikey

Personal LLM API gateway & proxy — one address + one API key for all your models. Forwards OpenAI & Anthropic calls to your backends with failover and a circuit breaker. Pure passthrough, no format translation. Self-hosted (CLI + web UI).

@ramsesy/deepseek-local-api

Convert DeepSeek Web Chat to an OpenAI-compatible local API and interactive CLI for any harness or agent

@justin06lee/yagami

Self-hosted Anthropic- and OpenAI-compatible API backed by your signed-in coding-agent CLIs, plus a zero-config library for driving them from your own apps — no API keys needed.

@realvendex/pi-token-router

TokenRouter.com unified API gateway as a native Pi provider for accessing 300+ LLM models via a single API key

aiplug

A lightweight runtime that unifies 490+ AI providers behind a single, OpenAI-compatible API.

omk-ai

Unified LLM API with automatic model discovery and provider configuration

@bismawy/pi-agentrouter

AgentRouter provider for pi — GPT-6 Astra, GPT-5.6 Sol, Claude Opus 4.8/5, DeepSeek V4 Flash and GLM 5.3 under one namespace, with self-healing WAF recovery (history redaction + auto-translation)

@lehcode/soakp

Secure OpenAI Key Proxy (SOAKP) facilitates secure usage of the OpenAI API key through a proxy-like application.

@code-yeongyu/senpi-ai

Unified LLM API with automatic model discovery and provider configuration

@deepseek-ai/dsh-http-proxy

Process-wide outbound HTTP proxy policy for DeepSeek Harness: resolve it from the launch environment and install it as undici's global dispatcher

@ai-sdk/gmicloud

The **GMI Cloud provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for [GMI Cloud](https://www.gmicloud.ai), offering GPU inference for open-weight models over an OpenAI-compatible API.

TriCacheLLM-MMA

A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap.

agentweave-router

Pre-inference routing for tool-rich LLMs and multi-agent systems with MCP, A2A, LangGraph, AutoGen, policy-aware routing, recovery, and reproducible evaluation.

More in Agent frameworks & infrastructure