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

How to build a custom agent tool on the harness library with Unreal Agent

Write a tool with a schema and translator that turns model tool calls into async operations.

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

Who it is forA Go engineer building an in-house agent that needs its own tools, such as a ticket lookup or a file workflow.

The problemAn off-the-shelf agent does not know the internal systems a team needs it to call.

The outcomeA custom tool registered with the harness, where translators validate calls and produce operations that run asynchronously.

What you need first

  • Go toolchain (inferred from the repo language)
  • git, to clone the repo
  • An LLM provider that the LLM Adapter can reach (the README does not name one)

Steps

  1. git clone https://github.com/unreallabsai/unreal-agent (inferred, check the README)
  2. Read the harness/ library and the glossary to learn the Tool, Tool translator, and Operation terms.
  3. Define your tool with a schema and bind it to a translator that performs no I/O.
  4. Make the translator return a tool call status and serializable operations, using the primitives in harness/primitives/ where they fit.
  5. Run the coordinator with your tool in the host-selected set and check that the operation result is formatted into the model result.

Prompt for your agent

In the unreal-agent repo at <repo path>, add a tool named <tool name> with a schema and a translator that returns serializable operations for <task>. Expected output: a model-facing result produced from the operation output. Verify that the translator performs no I/O and that the operation is serializable.

Caveat. The README states that translators must not perform I/O or suspend the event loop, so any external lookup belongs in an operation, not in the translator.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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