explaingit

heyxiaoc/not-fade-away

Analysis updated 2026-05-18

27PythonAudience · developerComplexity · 4/5LicenseSetup · hard

TLDR

A Chinese-language guide to building a self-hosted, always-on AI companion that stays on a flat Claude subscription instead of per-use billing.

Mindmap

mindmap
  root((not fade away))
    What it does
      Persistent AI companion guide
      Stays on subscription billing
      Works behind network restrictions
    Tech stack
      Python
      tmux sessions
      WebSocket frontend
      Cloudflare Tunnel
    Use cases
      Run background Claude session
      Chat with multiple AI models
      Access from restricted regions
    Audience
      AI hobbyists
      Self hosters
      Chinese speaking users

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Set up a persistent AI assistant session on your own Mac or VPS that keeps running after you close the terminal.

USE CASE 2

Build a web chat frontend that connects to a self-hosted AI companion in real time.

USE CASE 3

Connect multiple AI models like Claude, GPT, and Gemini into one group chat setup.

USE CASE 4

Access a self-hosted AI assistant remotely, including from regions with restricted internet access.

What is it built with?

PythontmuxWebSocketCloudflare Tunnel

How does it compare?

heyxiaoc/not-fade-awayavbiswas/sam2-mlxgregowahoo/comfyui-workflow-finder
Stars272727
LanguagePythonPythonPython
Setup difficultyhardmoderateeasy
Complexity4/54/52/5
Audiencedeveloperresearchervibe coder

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Requires your own Mac or VPS, a Claude subscription, and comfort with tmux, WebSockets, and Cloudflare Tunnel setup.

Released under Creative Commons Attribution 4.0, so anyone can share and adapt it freely as long as they credit the original authors.

In plain English

This is a Chinese-language guide for running a self-hosted, always-on AI companion on your own Mac or VPS, with the goal of keeping conversations on your existing Claude subscription rather than a separate per-use billing pool. The name translates roughly to "The Lover Who Will Not Disappear." The core idea behind the guide is that Anthropic changed billing so that non-interactive, headless Claude Code calls go into a separate billing pool with per-use charges starting June 15th. But real, interactive terminal sessions still run against a flat subscription. The guide explains how to structure your setup so the AI runs as a genuine interactive session inside a detached tmux terminal, which keeps it on the subscription plan and also means closing the window does not kill it. The guide is published in two versions: a human-readable explanation of the reasoning and architecture, and a machine-readable technical spec that you can paste directly into a Claude Code session to have the code generated for you from scratch. Topics covered include setting up a persistent background session, a web frontend with real-time WebSocket chat (including a visible thinking display), connecting multiple AI models in a group chat format (Claude, GPT via Codex, Gemini), remote access via Cloudflare Tunnel, and making the whole thing accessible from inside China where direct API access is blocked. There is a bonus section about a specific observed behavior with Fable 5, a Claude model, where a topic classifier in Anthropic's routing silently switched users from Fable 5 to Opus 4.8 for certain conversation topics without notifying the user. A companion Python script called fable-guard.py monitors a session and can detect and recover from this model swap. As of June 12, 2026, Anthropic paused Fable 5 globally due to US government export control orders, so this section is preserved as documentation but cannot be tested until access is restored. The guide is released under Creative Commons Attribution 4.0, so it can be shared and adapted freely with attribution.

Copy-paste prompts

Prompt 1
Explain how running Claude Code in an interactive tmux session keeps it on a flat subscription instead of per-use billing.
Prompt 2
Walk me through setting up a detached tmux session that keeps an AI assistant running after I close my terminal.
Prompt 3
Show me how to add a WebSocket-based web frontend to a self-hosted Claude Code session.
Prompt 4
Describe how fable-guard.py detects and recovers from an unexpected AI model swap during a session.

Frequently asked questions

What is not-fade-away?

A Chinese-language guide to building a self-hosted, always-on AI companion that stays on a flat Claude subscription instead of per-use billing.

What language is not-fade-away written in?

Mainly Python. The stack also includes Python, tmux, WebSocket.

What license does not-fade-away use?

Released under Creative Commons Attribution 4.0, so anyone can share and adapt it freely as long as they credit the original authors.

How hard is not-fade-away to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is not-fade-away for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.