Connect HoneyHive to Your AI Agent

Turn your supplied examples into dataset entries using a clear mapping between source fields and test sections.

6 tools API key

Try a HoneyHive Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill HoneyHive

Create a Dataset from Examples

Create a named dataset and insert supplied examples with a field mapping.

/oo HoneyHive: Create HoneyHive dataset [name] with description [description], then add these JSON examples [data], mapping [fields] to inputs, [fields] to history, and [fields] to expected answers.

Start Working with HoneyHive

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect HoneyHive

Connect a project-scoped HoneyHive API key from Settings > Project > API Keys.
Connect HoneyHive →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

Access to the HoneyHive project and source examples with known field names.
Updating a dataset’s datapoint list replaces the complete list. Removing an association leaves the datapoint itself intact.

HoneyHive Tools

This HoneyHive connection manages project datasets and datapoint associations. It can create datapoints from JSON examples but does not run evaluations or read execution traces.

Dataset Management

Find datasets by exact name or ID, create or edit them, and permanently delete selected datasets.

Datapoint Membership

Insert mapped examples and remove a selected datapoint’s association with a dataset.

6 tools

List Datasets

List HoneyHive datasets in the API key's project, optionally filtering by dataset ID or exact name.

honeyhive.list_datasets

Create Dataset

Create a HoneyHive dataset with an optional name, description, and initial datapoint identifiers.

honeyhive.create_dataset

Update Dataset

Update a HoneyHive dataset's name, description, or complete datapoint identifier list.

honeyhive.update_dataset

Delete Dataset

Permanently delete a HoneyHive dataset by its unique identifier.

honeyhive.delete_dataset

Add Datapoints

Create datapoints from raw JSON objects and add them to a HoneyHive dataset using a field mapping.

honeyhive.add_datapoints

Remove Datapoint

Remove a datapoint association from a HoneyHive dataset without deleting the datapoint itself.

honeyhive.remove_datapoint

Frequently Asked Questions

What mapping do my examples need?

Identify source field names for inputs, conversation history, and ground-truth answers. The mapping places those fields in the corresponding datapoint sections.

Does removing an example delete it?

Removing a datapoint association detaches it from the selected dataset without deleting the datapoint itself.

Can I run an evaluation here?

These actions manage datasets and examples. Evaluation runs and trace inspection are not exposed by this connection.