CLI

@postlyra/cli mines content ideas out of your own git history, on your own machine. Your commits never leave it. Only the finished ideas do.

$ postlyra mine
myrepo: 14 commit(s), 6 already mined, 8 new
website: 3 commit(s), 0 already mined, 3 new

Pushed 6 idea(s) — 6 new, 0 updated:
  - the queue timeout bug that cost a night of sleep
  - why I killed the Sunday cron in favor of a Friday button
  - a before/after on the onboarding flow's time-to-first-post

What it does

postlyra mine walks the git repos you point it at, pulls the commit subjects from the last N days, and asks an AI to turn that work log into content ideas: what happened, the angle that makes it worth posting, which pillar and format it fits, and for reels exactly what to screen-record.

Point it at a notes folder too and the notes you capture as you work get mined the same way. Commits tell it what you built. Notes tell it what you were thinking.

The finished ideas get pushed to your Postlyra account. The raw commits never do.

The privacy pitch

Postlyra cannot read your local git clones, and you should not have to hand a SaaS access to your repos just so it can read commit subjects. The CLI flips that around.

• Your commits are read locally, by git log, on your disk.
• They go only to the AI you already run and pay for: the claude CLI if it is on your PATH, or the Anthropic API if you set ANTHROPIC_API_KEY. Either way it is a call you control, to a provider you already trust with your code.
• Only finished ideas reach Postlyra: a headline, an angle, a pillar, a format, maybe a recording note. No commit messages, no diffs, no file contents, no repo names beyond the short label you configured.

If neither backend is available it refuses to run rather than quietly doing something else with your commit text.

See Privacy for exactly what crosses the wire.

Install

npm install -g @postlyra/cli
postlyra --help

Or without installing:

npx @postlyra/cli --help

Zero runtime dependencies. Requires Node.js 20 or newer.

Next

• Install and set up
• Commands
• Configuration
• How mining works
• Troubleshooting

CLI or MCP

Both push to the same place. Pick by how you work.

Use the CLI for habitual or scheduled mining, and anything unattended. It runs a whole window in one shot.

Use MCP when an agent is already reasoning about the material and can judge what is worth writing about, rather than mining a window blindly.