Zero-cost LLM routing across free-tier model APIs with Bifrost, certification scripts, and agent-ready fallback chains
Reusable starter kit for routing Hermes Agent through a local LiteLLM-based free/free-tier model router with clean aliases, fallback examples, systemd service templates, and terminal-first setup.
Backup brain for Claude Code. When your Claude Max plan hits its limit or Claude is down, flip one command and your claude -p agents keep running on a local mlx-lm model. Default Claude. Local only when needed.
🔀 Claude Code skill: route tasks to the best model via any OpenAI-compatible gateway (Claude/GPT/DeepSeek/Kimi/Qwen). 通用多模型路由 skill。
A lightweight portable POSIX terminal suite for custom OpenRouter provider routing, live cost/latency analytics, and preset management for Claude Code, Cline, and AI coding agents.
Claude Opus 4.6 + GLM 5.1 Cloud in a single Claude Code session. OAuth-preserving proxy, automatic model switching, four Opus-grade GLM subagents. No API key needed.
Hermes Agent setup that routes tasks between local Ollama/llama.cpp models and OpenAI Codex authority models to reduce cost, preserve privacy, and keep high-risk work verified.
Reproducible LLM routing + generation workbench (Docker, LiteLLM)
Add a description, image, and links to the llm-router topic page so that developers can more easily learn about it.
To associate your repository with the llm-router topic, visit your repo's landing page and select "manage topics."