Self-host OpenGrow to go from a brief to a published content pull request with your own AI keys
An open-source, self-hosted pre-alpha tool that turns a brief into an outline and Markdown draft, opens a GitHub pull request, and later ties content to traffic and Stripe revenue.
Evidence: The source shows its work: steps, screenshots, code or data you can inspect.
The business problem
A founder wants a repeatable pipeline from company context to published content, with some way to see which pieces drive pipeline and revenue.
What was tried
You write a brief, approve an outline, generate a Markdown draft with keyword research (scraped from Google Autocomplete and Bing), and approve it. OpenGrow opens a pull request in your content repository, and merging marks the piece as published. Attribution features include a tracking pixel, conversion capture, Google Analytics and Search Console import and Stripe revenue sync. It runs through Docker Compose with your own OpenAI, Anthropic or Google key, or free local models via Ollama, and an MCP server lets coding agents drive it.
What was reported (not reported)
The README reports no results. It says the core loop works locally and includes a demo animation.
Limitations
The project is labelled pre-alpha (v0.3.0) with one star at capture and an empty releases page, so it is early and unproven. GitHub pull request publishing is the first channel and others are planned. Lite mode is for personal use with weaker security. The licence is AGPL-3.0, with a commercial option. There are no benchmarks, customer outcomes or security audit.
What you need
Docker with Compose v2, at least one LLM API key or Ollama, and a GitHub token with contents and pull request write access. Lite mode needs about 2 GB of RAM, and production mode about 8 GB.
Sources
- GitHub (opengrowhq/opengrow) ↗ Code repository, publication date unknown
Source published: unknown. Last reviewed here: October 11, 2026. Spot a mistake? Tell us.
Tools in this workflow
- GitHub: Receives the draft as a pull requestTry GitHub
- Ollama: Optional free local modelsTry Ollama
Related workflows
Set up Hermes Agent on a cheap VPS with Telegram, morning cron briefings and a reusable content research skill
A 14-day test of Hermes Agent on a small VPS, reached through Telegram, with memory files, a daily and weekly briefing, and custom skills for content research.
Chain Hermes agents through Telegram into a research, writing, editing and publishing team
A business-automation blog shows how to let several Hermes agents message each other in Telegram so a research agent can hand work to a writing agent in a content pipeline.
Set up OpenClaw as an always-on agent for client onboarding, KPI snapshots and content drafts, with approval steps
A hosting company's tutorial lists 25 OpenClaw workflows, including scheduled KPI posts, client onboarding folders and emails, expense logging and content repurposing, with security advice for running it safely.
Build a Claude Code subagent that writes SEO and answer-engine research briefs with Perplexity and Firecrawl
A step-by-step build of a Claude Code subagent that, given a post or topic, gathers search trends and search results and writes a research brief with keywords, snippet opportunities, competitor gaps and a suggested title and slug.