Who it is forAn analyst who starts a task in the browser and an engineer who needs to pick it up from a terminal.
The problemCopying context between tools loses history and decisions.
The outcomeThe terminal session shows the same history, tool records, and results as the Web thread, and new terminal messages appear in the Web thread.
What you need first
- Node.js 24.10 or newer
- pnpm 10.34.5
- Native build tools for your platform
- A cloned copy of the agnes-harness source repository
- A configured AI model in the Web interface
Steps
- Run
node packages/cli/dist/local/agnes.mjs serveand keep it running. - In the browser, start a task and note its session.
- Open a second terminal in the same source directory and use the same AGH_HOME or AGNES_PROFILE values if you set them.
- Resume the Web session in the terminal with /resume.
- Run
node packages/cli/dist/local/agnes.mjs -p "Briefly explain what this project does"and check that it appears in the Web thread.
Prompt for your agent
Using the agnes-harness repository at <repo path>, start the AGH server, create a task in the Web interface, then resume that session from the CLI with /resume. Expected output: the terminal shows the earlier history and the new message appears in the Web thread. Verify both views show the same session ID.
Caveat. The CLI must use the same backend and configuration as the running Web server, so mismatched AGH_HOME or AGNES_PROFILE values will show a different session.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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