lincwang123-bot GitHub avatar

humanized-social-publisher

lincwang123-bot

A locally run, agent-oriented Chinese social media publishing assistant that automates content upload and scheduling for Xiaohongshu, Douyin, and WeChat Channels through observable browser flows while requiring final manual confirmation by default.

Stars

7

7-day growth

No data

Forks

2

Open issues

0

License

MIT

Last updated

2026-07-31

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It treats safety and account integrity as core design constraints rather than afterthoughts, with identity checks, per-account browser profiles, deduplication, throttling, and human-like interaction pacing, all without claiming to bypass platform detection.

Who it is for

  • Content operators managing multiple Chinese social media accounts
  • Developers building AI-agent-assisted publishing workflows
  • Individual creators who want scheduled multi-platform posting with manual oversight
  • Teams needing a local, inspectable content distribution pipeline

Use cases

  • Scheduling Xiaohongshu, Douyin, or WeChat Channels posts to a future local time
  • Letting an AI coding agent configure and prepare publishing tasks under explicit AGENTS.md guidance
  • Preflighting post packages to verify platform, media, cover, and account routing before upload
  • Running a local queue of publishing jobs with retry, cancel, and visual status inspection

Strengths

  • Default manual confirmation and explicit two-flag opt-in for auto-publish reduce accidental final submissions
  • Per-account isolated browser profiles and identity_hint matching help prevent cross-account posting errors
  • Humanized interaction pacing is configurable and designed for observability, not stealth
  • Local sanitize checks and .gitignore rules protect credentials, paths, and user media from being committed

Considerations

  • Platform creator backend changes can break selectors, so adaptation is best-effort and important accounts should keep human review
  • The project does not provide anti-detection, fingerprint spoofing, or CAPTCHA bypass, and cannot guarantee account safety
  • Requires Python 3.10+ and command-line setup, which may be a barrier for non-technical users

README quick start

快速开始

Description

Agent-friendly local publisher for Xiaohongshu, Douyin and WeChat Channels with multi-account safety, scheduling and deduplication.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
mshumer
Featured
mshumer GitHub avatar

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents
1,234