DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run one chat assistant across a project folder with Spynel

Install Spynel and talk to one assistant that coordinates your coding harnesses in a single terminal chat.

Remote script. The curl install pipes a remote script directly into sh, so review the script at its URL before running it on a machine that matters.

Who it is forA developer juggling several AI coding chats and projects who wants one place to direct all of their AI work.

The problemWork is spread across separate AI chats, projects, and spaces, so context gets lost and switching costs time.

The outcomeA running Spynel terminal chat, scoped to your project directory, that acts as the single assistant for that project's AI work.

What you need first

  • macOS or Linux for the curl install, or Node.js 18+ for the npm install
  • An existing coding harness such as Codex or Claude Code, since Spynel uses them to do the work
  • A project directory to run Spynel from

Steps

  1. Run curl -LsSf https://spynel.agent-zero.ai/install.sh | sh on macOS or Linux, or run npm install -g spynel with Node.js 18+.
  2. Change into your project directory.
  3. Run spynel from that directory.
  4. Run /config in the chat to complete setup.
  5. Send your next request to the assistant in the chat instead of opening a new AI chat.

Prompt for your agent

Using the spynel repo at agent0ai/spynel, install Spynel in <project-directory> and start it with `spynel` from that folder. Expected output: a running Spynel terminal chat bound to <project-directory>. Verify that `/config` opens and that a test message gets a reply from the assistant.

Caveat. Spynel has no AI of its own, so it only works once a coding harness such as Codex or Claude Code is available to do the work.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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