Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 18 of 41
A tiny, stateless API that gives OpenAI, Claude, Gemini, xAI and Ollama one simple text-in/text-out contract.
Pool multiple free-tier LLM API providers behind one OpenAI-compatible endpoint, with automatic failover and a live dashboard.
Route Codex tasks between GPT-6 Astra and GPT-5.6 Sol by expected rework cost, then delegate bounded repetitive work to GPT-5.6 Luna.
A multi-protocol-compatible middleware for LLM services.
Stop using an LLM for every decision. ThinkLess learns your AI agent's routine LLM decisions and answers them locally once proven, with one line under the OpenAI or Anthropic client. Or run typed decisions through rules and small models first. Lower LLM cost and latency, every decision traced.
Cost-aware hybrid router for multi-agent LLM systems: keyword → embedding → LLM cascade. Matches LLM-only accuracy (82.6% vs 82.9%, McNemar p>0.3) with 74% fewer LLM calls on CLINC150.
Intent detection agent that will route irrelevant queries to a cheaper model.
Bio-inspired multi-agent orchestration — 4 neuromuscular mechanisms for intelligent LLM routing
Smart Codex OAuth routing for OpenClaw - add more accounts, route work to the best available one automatically, and keep serious workflows moving without API keys or manual account juggling.
MonkeysLegion-Apex is a provider-agnostic AI abstraction layer that unifies LLM interactions across Anthropic, OpenAI, Google (AI Studio + Vertex AI), and Ollama behind a single, type-safe PHP 8.4 API.
Notes and small projects from running multi-model LLM agents: deployment, model routing, and cost control.
Roteador Inteligente de CLI Agents — Nunca mais escolha qual ferramenta usar
Local HTTP CONNECT proxy with WireGuard support, SPA dashboard, and runtime allowlist management for controlled residential egress.
Wormholes for Interstellar Gateway for AI Agents -- https://github.com/talhaHavadar/interstellar
Llimona is an open and modular Python framework for building production-ready LLM gateways
Universal LLM provider compatibility layer — normalizes provider-specific payload differences (thinking formats, output budgets, tool pairing, media transport) into a single first-match-wins dispatch pipeline. Plus dynamic version detection with strategy-pattern version parsing.
🏓 Bounce — Multi-layer AI provider failover gateway. UPS for your LLM tools. 多级 AI 提供商故障转移网关,让你的爱AI永不停机。
Valid tool calls from any local model — a drop-in OpenAI-compatible proxy for Ollama that guarantees well-formed tool calls and restores tool_choice.
Local multi-protocol LLM API tester for OpenAI-compatible, Anthropic & Gemini endpoints · 本地多协议 API 测活工具
检测中转站的 DeepSeek 是满血还是野鸡:用 DeepSeek Harness minimal 预设的首轮请求面做思维链行为指纹。支持 OpenAI / Anthropic / Responses 三种协议,零依赖,带网页界面。Detect downgraded or rebadged DeepSeek models behind API relays.
Local traffic runtime for Claude Code and Codex — capture, route, transform, and inspect AI provider traffic on macOS.
Find the best and newest models for oh-my-openagent (OMO) configurations using Artificial Analysis data
Smart LLM and cloud code optimization tool that cuts token costs by up to 75%. Perfect for AI developers seeking maximum efficiency and lower expenses in 2026.
DeepSeek API peak/off-peak pricing tray app & alerts (Win/Mac)
A GOST Rewriter HTTP plugin that converts bidirectionally between OpenAI Chat Completions and Anthropic Messages API formats
Unified cost-aware router: model x reasoning-depth on one Thompson bandit (factored policy), bi-temporal forget-on-drift statistics memory + auto-drift proxy, GRPO-internalized Qwen3-4B depth policy.
A highly specialized, production-grade AI SDK provider designed for Azure AI Foundry and Azure OpenAI-compatible endpoints
Open-source CLI to switch API keys, proxy and relay endpoints, and models for OpenAI Codex and Claude Code.
高性能本地 LLM API 网关(Rust)—— 同时提供 OpenAI 兼容与 Anthropic Messages 端点,按提供商维护智能负载均衡的 API-Key 池,支持流式输出,内置 Web 控制台。 | High-performance local LLM API gateway in Rust — OpenAI-compatible and Anthropic-Messages endpoints with smart load-balanced per-provider API-key pools, streaming, and a built-in web console.
Fix models missing from the Hermes Agent /model picker (the two-cache gotcha) and list the newest 100 OpenRouter models chronologically. Zero dependencies.
Get 1.5 Billion free AI tokens/month — one local endpoint for Claude, GPT, Gemini and 500+ models
To convert API requests from the OpenAI Chat Completions format to the Google Gemini format
docker region:us
docker region:us
docker region:us
docker region:us
docker region:us
docker region:us
docker region:us
docker region:us
docker region:us
docker region:us
gradio region:us
docker region:us
docker region:us
docker region:us
static region:us
Bifrost review: compare features, pricing, use cases, access model, and alternatives for this LLM agent in 2026. Bifrost is a high-performance LLM gateway that connects 1000+ models through a single API interface
AnyModel review: compare features, pricing, use cases, access model, and alternatives for this Model Serving agent in 2026. All-In-One AI Comparison Tool: Use and compare all the top AI models side-by-side with one account
One API to use many AI models with better prices and reliability.
Easily build, manage, and monitor all your AI applications.
Compare 50+ AI models at once for the best results.
Get all top AI models in one place, with one simple subscription.
Connect to 100+ AI models easily with one unified interface.
LLM routing: Neural router for AI agent orchestration - FastGRNN-based intelligent routing with circuit breaker, uncertainty estimation, and hot-reload
Auto AI Agent 网关 CLI(WebSocket,独立二进制,无需 Bun)
AI Agent Switch CLI/TUI control plane for switching AI coding agent providers and models.
CLI binary (amux) for agent-mux
Gateway package for remote and browser-facing agent-mux surfaces
OneKey Gateway CLI and SDK for routing AI agent, MCP, Skills and LLM requests by DeepNLP x AI Agent A2Z
OpenAI LLM provider (ILlm) for @mcp-abap-adt/llm-agent.
Anthropic (Claude) LLM provider (ILlm) for @mcp-abap-adt/llm-agent.
SAP AI Core LLM provider (ILlm) for @mcp-abap-adt/llm-agent.
DeepSeek LLM provider (ILlm, extends OpenAIProvider) for @mcp-abap-adt/llm-agent.
An HTTP(s) proxy `http.Agent` implementation for HTTP
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Maps proxy protocols to `http.Agent` implementations
Global HTTP/HTTPS proxy configurable using environment variables.
A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS
A PAC file proxy `http.Agent` implementation for HTTP
[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c
Get a user agent string across all JavaScript Runtime Environments
A ready to use http and https agent for working with proxies that keeps connections alive!
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n
Smart LLM router — save 84% on inference costs. 91 models (8 free). Pay by credit card (API key) or USDC (x402 wallet).
Use OpenAI, Anthropic, xAI, OpenRouter and AI Gateway models (100+), external coding agents (Claude Code, Codex, fx) and durable workflows with Google ADK for TypeScript
HTTP proxy tunneling agent.
Databricks provider for Vercel AI SDK
A universal LLM client - provides adapters for various LLM providers to adhere to a universal interface - the openai sdk - allows you to use providers like anthropic using the same openai interface and transforms the responses in the same way - this allow
The OpenRouter TypeScript SDK is a type-safe toolkit for building AI applications with access to 400+ language models through a unified API.
Octoryn LLM official command-line interface
A cacheable dns.lookup(…) that respects TTL
Maps proxy protocols to `http.Agent` implementations
AI SDK v7 provider for Claude via Claude Agent SDK (use Pro/Max subscription)
Adaptive LLM router with tier-based model selection and fallback support.
Unified LLM API for Anthropic, OpenAI, Google, and DeepSeek. Streaming, retry/backoff, structured output, token normalization. © Diabolical Labs
Open source cost intelligence proxy for AI agents. Cut LLM costs ~80% with smart model routing. Dashboard, policy engine, 11 providers. MIT licensed.
NebulaOS LLM Gateway provider - OpenAI-compatible chat completions
OpenAI-compatible proxy for Cursor CLI — use Cursor models from any LLM client on localhost
JWT-authenticated credential proxy for upstream LLM providers
A lightweight Node.js wrapper for routing HTTP(S) traffic through Tor, including optional ControlPort circuit rotation.
OpenRouter integration for LangChain.js
Fireworks integration for LangChain.js
A SOCKS proxy `http.Agent` implementation for HTTP and HTTPS
Node HTTP/HTTPS Forward Proxy Agent
RFC-respecting User-Agent serialization and deserialization
An HTTP(s) proxy `http.Agent` implementation for HTTPS
TypeScript definitions for tunnel
LangChain chat model for OpenAI via OAuth (ChatGPT Plus/Pro)
A companion library to openai for Azure OpenAI.