Self-hosted, OpenAI-compatible LLM gateway that turns every request into a payload-free, attributable cost receipt — no stored prompts or responses. Apache-2.0, zero dependency on any Inferrail-operated service. Also offers a hosted x402 capability, Work Economics, for AI job cost receipts (Base Sepolia testnet).
Latest release v0.1.2 — Inferrail v0.1.2 · 24 Aug 2026
1 file for Claude Code: inferrail CLAUDE.md — 802 tokens loaded in every session.
CLAUDE.md A 802 tok These files are domondi1/inferrail's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.