DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to call the agent from a shell script with print mode and JSON with Star CLI

Run one prompt with star -p and --json, then parse the NDJSON output in a script.

Authorization notice. Star CLI is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. Keep provider API keys in environment variables or ~/.star-cli/.env, never hard-coded in the script or committed to git.

Who it is forA developer automating a repeated text or code task who needs the agent to run unattended inside a script.

The problemThe interactive REPL cannot run unattended, so a script needs a non-interactive entry point.

The outcomeA script that runs one prompt and reads machine-readable NDJSON lines.

What you need first

  • Node.js 20 or newer
  • pnpm, only if you build from source
  • An API key for an OpenAI, Anthropic, or OpenAI-compatible provider, set via /connect or config.toml

Steps

  1. Install the CLI with npm install -g @cryer/star-cli.
  2. Store your provider key in an environment variable or in ~/.star-cli/.env, using /connect in the REPL once.
  3. Run star -p "hi" to confirm that print mode works.
  4. Add --json to the same command, for example star -p "<your prompt>" --json, to get NDJSON output. (inferred, check the README)
  5. Parse the output line by line in your script and handle each JSON object.

Prompt for your agent

Using the cryer/star-cli repo, write a shell script that runs `star -p "<prompt>"` with --json and writes the output to <output-file>. Verify that every output line parses as valid JSON.

Caveat. The README mentions --json for scripting but gives no example combined with -p, so test the exact flags before you rely on them.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page