# tsingyuai/growth-lab

An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews results to improve the next round of growth. 从代码到市场的开源端到端增长工具。理解产品、接入信息渠道、研究市场、执行增长行动，并基于真实数据自我改进。

Repository: https://github.com/tsingyuai/growth-lab
Canonical: https://ross.abutalabs.com/products/growth-lab
Homepage: https://growthlab.tsingyuai.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agentic-marketing, ai-agent, claude-code, codex, growth, growth-hacking, marketing-automation, open-source, seo, skills, xiaohongshu
Last push: 2026-08-11T04:56:57+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 2
- inputs: {"age_days": 40, "days_push": 22, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1861, forks 169 (observed 2026-08-28T04:05:45.344384+00:00)

## What it is
Growth Lab is an open-source, end-to-end AI growth system that runs product marketing and user-acquisition loops through natural-language conversations with coding agents like Claude Code and Codex. It organizes skills, external clients (browser, APIs, content platforms), and persistent file-based memory into observe-act-review loops covering channels such as SEO page growth and Xiaohongshu content research, creation, and publishing.

## Use cases
- run an end-to-end growth loop for my product from my code repo
- research high-performing Xiaohongshu content and generate posts with images
- automate SEO page creation and track impressions and clicks
- review past campaign results and decide the next growth action
- audit which API keys and clients my growth setup is missing
- collect market evidence and turn it into content strategy
- keep product context and growth memory across AI sessions

## When to choose
- you want a self-improving marketing/growth loop driven by Claude Code or Codex
- you need SEO or Xiaohongshu content workflows with persistent memory and result review
- you prefer open-source tooling where all data and artifacts stay in your own workspace
- you want to drive marketing execution entirely through natural language

## When to avoid
- you need a polished hosted dashboard or no-code marketing suite
- your channels are not SEO or Xiaohongshu and you cannot build custom skills
- you require fully autonomous unattended operation rather than conversational collaboration
- you cannot provide local credentials for browser clients or image-generation APIs

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, web-scraping, nlp, llm-inference, prompt-engineering, mcp, analytics
- domain: large-language-models, developer-tools, analytics, crawlers
- platform: python, cli, cross-platform
- tags: growth-hacking, marketing-automation, claude-code, codex, agentic-marketing, seo-automation, xiaohongshu, skills, self-improving-loop, open-source, seo, ai-agents, automation, marketing, docker

## Member repositories
- tsingyuai/growth-lab (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:45.344384+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:15:51.666300+00:00, confidence not recorded.
  - readme: https://github.com/tsingyuai/growth-lab (fetched 2026-08-28T04:05:45.344384+00:00, sha 92d521cc716b)
  - homepage: https://growthlab.tsingyuai.com (fetched 2026-08-29T10:55:00.486075+00:00, sha b700a2beaf39)
- Data as of 2026-08-30T08:39:29.467469+00:00.