mildsky7777-max/house-x-template — explained in plain English
Analysis updated 2026-05-18
Automatically post 8 to 15 AI-drafted tweets a day without manually writing each one
Filter out AI-sounding language and banned phrases before anything goes live
Let the system adjust its own posting rules weekly based on which posts got engagement
Reply automatically to verified accounts to build engagement
| mildsky7777-max/house-x-template | 0xhassaan/nn-from-scratch | 3ks/embedoc | |
|---|---|---|---|
| Stars | 0 | 0 | — |
| Language | Python | Python | Python |
| Last pushed | — | — | 2023-06-08 |
| Maintenance | — | — | Dormant |
| Setup difficulty | moderate | moderate | hard |
| Complexity | 4/5 | 4/5 | 1/5 |
| Audience | pm founder | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Uses Playwright browser automation instead of a paid X API tier.
House Stack is a Python-based X (Twitter) automation template aimed at indie builders who want to grow an account consistently without manually writing and scheduling every post. It is described as built by a Korean indie builder targeting 100K or more followers, and is released under the MIT license. The system runs five layers. A capture layer runs hourly, scraping trending topics, personalized feed recommendations, specific orbit accounts, and engagement notifications. A generation layer uses scheduled prompts to select and polish drafts from a queue file (drafts.json), then posts them via Playwright, a browser automation library, so no paid X API tier is required. A quality layer runs a gate before each post that checks for over 50 AI-sounding language patterns (such as "delve," em-dash overuse, and parallel symmetry), Korean machine-translation patterns, and banned phrases. An 8-reviewer council evaluates drafts on substance, brand fit, hook strength, risk, and authenticity. An engagement layer sends rate-limited automatic replies to verified accounts at 5 to 10 per hour. The fifth layer is self-evolving: 24 hours after a post goes live, a script scrapes engagement metrics and scores them using a weighted formula (replies and bookmarks weighted more heavily than likes). Results are logged as experiments. A weekly automated retrospective reads those logs, proposes rule changes, and writes them back to a central mandates file, creating a feedback loop that adjusts posting rules based on actual performance. Daily post volume targets 8 to 15 posts. Multiple voice modes are enforced by the quality gate.
An X automation template that scrapes trends, drafts posts with AI, screens them for quality, and self-tunes its own posting rules from engagement data.
Mainly Python. The stack also includes Python, Playwright.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.
Mainly pm founder.
This repo across BitVibe Labs
Verify against the repo before relying on details.