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

How to add a business tool to the agent as a plugin with Agnes Harness

Register a customer-specific tool as a backend plugin so the agent can call it.

Who it is forA solutions engineer whose customer needs the agent to query an internal order or knowledge system.

The problemWriting customer systems directly into the agent means forking it for every deployment.

The outcomeA backend plugin registers a tool the agent can call, and each call keeps its inputs and structured output.

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

  1. Clone the Agnes Harness repository and open its root directory.
  2. Run pnpm install --frozen-lockfile.
  3. Run pnpm --filter @agnes/cli build:local.
  4. Read the backend plugin guide at docs/develop/backend.md and start from the demo_text_stats example.
  5. Run node packages/cli/dist/local/agnes.mjs serve, open the printed loopback URL, and call your tool in a task.

Prompt for your agent

Work in the agnes-harness repository at <repo path>. Follow docs/develop/backend.md to add a backend plugin that exposes a tool named <tool name> for <business system>. Confirm the tool appears in a task and returns structured output. Report the files you changed.

Caveat. AGH is a pre-alpha developer preview, and ordinary backend plugins run as trusted in-process code, so review plugin code before enabling it.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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