quantum-free-router
A Bifrost-based, OpenAI-compatible free-tier LLM router for long-running coding and research agents, packaged with a curated model catalogue, install scripts, health checks, systemd setup and model-certification tools.
Installation & usage
README summary
A Bifrost-based, OpenAI-compatible free-tier LLM router for long-running coding and research agents, packaged with a curated model catalogue, install scripts, health checks, systemd setup and model-certification tools.
A professional free-tier LLM router for long-running coding and research agents. Packages a Bifrost-based OpenAI-compatible router with a curated free-model catalogue, install scripts, health checks and certification tools. One local OpenAI-compatible base URL (http://127.0.0.1:4000/v1). Providers: OpenCode Zen, KiloCode, NVIDIA NIM, Gemini, Mistral, Cerebras, Groq, SambaNova, Cohere. Bounded timeout / retry settings and model-certification scripts. One-command install and systemd service setup. Keeping an agent task alive when a single free model goes down, times out or hits its quota mid-run.
Auto-extracted from the repository README. The authoritative steps live in the repository on GitHub.
Full README
quantum-free-router
A professional free-tier LLM router for long-running coding and research agents. Packages a Bifrost-based OpenAI-compatible router with a curated free-model catalogue, install scripts, health checks and certification tools.
What's inside
- One local OpenAI-compatible base URL (
http://127.0.0.1:4000/v1) - Providers: OpenCode Zen, KiloCode, NVIDIA NIM, Gemini, Mistral, Cerebras, Groq, SambaNova, Cohere
- Bounded timeout / retry settings and model-certification scripts
- One-command install and systemd service setup
Use it for
Keeping an agent task alive when a single free model goes down, times out or hits its quota mid-run.