llm-router

Connect Your Agents And Harnesses With Any Provider 🦚

The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM platforms with automatic fallback, key scheduling, rate-limit tracking and encrypted credential storage.

Free, self-hosted AI model router. OpenRouter / ClawRouter alternative using your own API keys. 14-dimension classifier routes to the right model (Anthropic/OpenAI/Kimi) automatically. No middleman, no markup. Built for OpenClaw.

Open-source Fugu: the open-source LLM orchestration brain.

Use Claude Code, Codex, OpenCode, Cline for free — one local gateway to 14+ free LLM providers. OpenAI & Anthropic compatible.

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover, content-aware routing and an honest per-model compatibility doctor

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.

Local-first AI Gateway: Connect Claude Code, Cursor, Windsurf, & Cline to Antigravity, OpenAI, Claude, & Gemini. One endpoint, OAuth auto-refresh, quota pooling & failover.

Use Claude Code and Codex as the foundation for coding infrastructure, allowing you to decide how to interact with the model with flexible routing and configuration. 中文版： 以 Claude Code 和 Codex 作为编程基础设施的基石，自主选择交互的模型与提供商，并享有灵活的路由与配置。

Open-source, self-hosted BYOK LLM API router with an OpenAI-compatible interface, multi-provider failover, model aliases, circuit breakers, usage analytics, and secure key management.

Storefront for unorouter.com. Next.js 16, React 19, Tailwind v4 frontend for browsing and purchasing AI model access.

AI-routed gateway for free LLM APIs — reads your prompt and routes it to the best free model (Gemini, Groq, Cerebras, NVIDIA NIM, Mistral, OpenRouter, GitHub Models). OpenAI-compatible, streaming, key pooling, persistent quota tracking.

Self-hosted AI gateway for agents — route providers, virtual models, limits, and usage from one console.

自托管 OpenAI-compatible AI Gateway：用 auto / auto-coding / auto-longtext 自动选择合适模型，支持流式、工具调用、多模态透传和 fallback。

🌊 月汐（kimi-tide）— DSH 的「每一步自动选模型」插件：贴图自动走能看图的模型，写代码走编码模型，闲聊翻译走便宜模型，每次选了谁、为什么，面板看得见 · The per-step model router for DeepSeek Harness: any connected model, routed by your rules

Smart LLM router for AI agents — automatic model selection on every request: classify, hard-filter on capability, then rank on task fit, cost, speed and reliability. Deterministic and local, <1ms, no inference call. Powers ClawRouter, Franklin, Hermes and dsh-clawrouter.

Multi-provider AI orchestration for VS Code — route to DeepSeek, Moonshot/Kimi, Alibaba/Qwen, Tencent/Hunyuan, and more with swarm intelligence, self-healing, and sovereign privacy. Built by Eternal Harmony AI for the global developer community.

Intelligent per-turn LLM model router for the pi coding agent. Auto-selects high/medium/low tiers with Ollama sync, rate-limit fallback, and feature toggles.