Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 37 of 41
Turn a supported ChatGPT/Codex OAuth sign-in into a private OpenAI-compatible endpoint, starting with self-hosted n8n.
OpenAI fast mode toggle for pi - Enables priority service tier on supported GPT-5 and GPT-6 models
Vercel AI SDK provider adapter for openai-oauth auth handles.
OpenAI and OpenAI-compatible AI provider adapters for AgentProdReady (chat, tools, streaming, embeddings).
Universal AI coding-agent runtime and model-routing layer for Claude, Codex, AGY, ZCode, and compatible runtimes.
Local Codex auth-file auth handle for openai-oauth.
An open-source resource scheduler and traffic-shaping proxy for AI agents
Kimi Code models in pi-coding-agent with OAuth, K3, K2.7, and HighSpeed selection
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 serving client — OpenAI-compatible inference client with multimodal support
OpenAI provider for BindAI
OpenAI-compatible API server for the Claude Code CLI — streaming, tools, vision, and live session reuse.
LiteLLM Databricks provider with live endpoint discovery and fuzzy model resolution
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
llama-index llms TrustedRouter integration
Resilient Multi-Provider LLM Fallback Router (DeepSeek, OpenAI, Ollama, Anthropic).
LLM plugin for Microsoft Foundry models, authenticated via Azure CLI
Lightweight provider router foundation.
Unified interface for interacting with multiple LLM providers.
Needlepath context selection as a LiteLLM proxy CustomGuardrail.
Official Python SDK for the Centralized LLM Platform
TTTPS Proof-of-Time reverse proxy for Ollama: cryptographic audit-trail timestamps for local model responses via the public KPP Provenance API
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.
OpenAI provider plugin for Shiro.
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.
The single model seam: budget, tracing, idempotency, adapters. Implemented in S7.
A unified LLM wrapper for online APIs and local models
通过openai兼容的api代理运行claude code, 不修改claude code的配置
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
Bill LiteLLM LLM proxy calls via U.CASH pay-per-token. Non-custodial.
Resolve llm model API keys from 1Password op:// references
Provider-neutral synchronous chat adapters for OpenAI, Claude, DeepSeek, OpenRouter, and LiteLLM.
Lightweight extraction of sglang's reasoning/tool-call parsers and chat template rendering for router services.
Local sidecar giving any tool grounded, cited, routed AI — Ollama or OpenRouter, no API key required.
Share an LLM API quota across devices on a local network (Wi-Fi hotspot, USB tether, or LAN)
Provider-routed LLM request retry policy for the DeepSeek Harness
Provider-neutral LLM service interface for the DeepSeek Harness
Multi-provider language generation toolkit using Vercel AI SDK - generate responses with 10+ LLM providers including OpenAI, Anthropic, Google, and more.
pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)
DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam
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
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.
API gateway: the ApiProxy contract (api/), the fetch carrier pair (fetch/), and the host-side gateway plugin providing ctx.apiProxy
## Overview
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|
OpenAI provider for chai-ai.
Minimal Pi extension for OpenAI Fast mode.
This is the OpenAI provider for the Rabbit Agent SDK.
Improve OpenAI in pi with fast mode, usage stats, realtime voice, image generation, and footer polish.
OpenAI-compatible chat completions provider adapter (OpenAI and any compatible endpoint) with streaming and tool calls.
OpenAI model provider adapter for @purista/harness.
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).
Provider-neutral AI contracts for AgentProdReady — execute, stream, tools, and embeddings without vendor lock-in at the boundary.
@ai-sdk/anthropic with all dependencies updated to latest
Bridge OpenAI tools to Claude Code SDK, Codex CLI, and OpenRouter
TokenAllot CLI — wrap Claude Code, bind work items, check gateway health.
TokenAllot FastAPI gateway (vaults ANTHROPIC_API_KEY; enforces from signed policy cache; §12.1)
Agnos Proxy - the gateway-agnostic control plane for LLM routing, cost-tracking and observability. OpenAI-compatible governance proxy over a swappable BackendEngine.
LLM infrastructure layer with multi-provider fallback, health monitoring, speed probing, and alerting.
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.
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 integration
Remaining LLM providers plugin (RFC-0019, M6): OpenAI-compatible presets + Bedrock + Vertex, no new architecture
Azure OpenAI adapter for Zhivex AI SDK.
Server-side provider adapters for Charivo
Stateful Node.js sessions for Codex, Claude, Grok, Bedrock, and Responses-compatible model providers.
SAP AI SDK integration with the official OpenAI npm package for Azure OpenAI on SAP AI Core
LaunchDarkly AI SDK OpenAI Provider for Server-Side JavaScript
Cost-aware, local-first routing plugin for opencode with cheapest-capable frontier fallback and multi-agent orchestration.
pi extension that routes model calls through the Constructive metered gateway, so a pi session is metered exactly like agentic-server traffic
Typed, async Python SDK for AWS Bedrock.
Python SDK for the DhivehiGPT API
τ-llm: Unified LLM provider abstraction (OpenAI-first)
Spec-driven SDK for the gptproto async media generation API
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
Declarative runtime-state management for a LiteLLM proxy: reconcile users/teams/keys/credentials/models from a YAML spec.
One vendored litellm-catalog snapshot + one public overlay + shared lookup/cost math for portfolio LLM pricing
Unified LLM abstraction with provider pattern for portfolio projects
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 integration
Multi-provider LLM adapter plugin for Spakky Agent
Local LiteLLM proxy for GitHub Copilot models with OpenAI and Anthropic-compatible APIs.
Provider-neutral LLM service interface for the DeepSeek Harness
LangChain integration for the LLM7 Chat API
The sole Custom GPT Actions HTTP ingress and OpenAI transport anti-corruption layer.
Fireworks AI provider extension for pi - Access Kimi, MiniMax, GLM, DeepSeek, and GPT-OSS models through the Fireworks AI API
Groq adapter for @warlock.js/ai (OpenAI-compatible, thin wrapper over @warlock.js/ai-openai)
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
零依赖的 OpenAI 兼容模型智能路由调度器
Small completions-style Python interface backed by the Claude CLI
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Official Mistral API package for llm-api-adapter
A CLI and SDK for routing LLM calls and gating according to price.
Parse, normalize, and compare llm:// references (llmns, a name system for language models)
Central provider, model and application routing policy for Subactor LLM consumers.
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
Enterprise Autonomous Multi-Model AI Agent Gateway Engine
让任意 AI Agent 直接调用 focalapi 创作模型的命令行工具
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.
Provider-neutral LLM service interface for the DeepSeek Harness