vLLM-backed self-hosted inference server — OpenAI-compatible API, model registry, request observability, SSE streaming, and a Textual TUI playground for real-time model comparison.
Instructions file CodexOpenCode
Instructions for coeusyk/inference-x, covering openspec agent instructions for inferencex, working agreement, agent tooling (mandatory — token efficiency), two command paths only — no third and rtk proxy (rtk-ai/rtk).
Instructions file
Instructions for coeusyk/inference-x, covering claude.md — inferencex, tooling (mandatory every session), two paths only — no third, token-savior mcp (if present) and why.