Can Hermes drop a production table by accident?

Only the operations you allowlist reach the agent, so you can expose Create Dataset and Create Table while keeping Delete Table and Delete Dataset off. Give it the destructive operations only when a cleanup job actually needs them. The BigQuery credential resolves server-side and never rides the model.

Can the agent read rows out of BigQuery?

Not with these operations. The BigQuery tools here manage objects and jobs, so it can create and delete datasets, tables, routines, and models, plus cancel and delete jobs. The data it works from comes in through the sheet using Read Multiple Sheet Ranges.

Which Google account does it write to?

The Google Sheets credential you connect, resolved server-side at run time. The agent never sees the token, it just calls the operations you exposed, like Append Rows to Sheet or Write to Multiple Sheet Ranges.

Hermes is an open agent based on Nous Research’s Hermes models. NoClick runs it for you and adds your connected apps as tools.

How do I give Hermes access to an app?

Connect the app's integration node to the agent's tools handle and pick the operations to expose. Each becomes a callable tool.

Do I need my own infrastructure?

No. The harness runs in a hosted sandbox and NoClick handles credentials for the apps you connect.

Can Hermes use multiple apps at once?

Yes. Wire in several integrations and the agent can use them together in a single run.

Connect Hermes to Google BigQuery and Google Sheets

Give Hermes your BigQuery and Google Sheets at once and it can turn a plan in a spreadsheet into real warehouse structure. It reads a table spec from a sheet, creates the matching BigQuery datasets and tables, and appends what it did back to a log tab. BigQuery holds your data objects and Sheets is where people plan and review, so the agent moves work between the two without you copying names by hand. It also handles the cleanup side, deleting old tables and routines when a sheet says they are done.

Loading preview…

Opens a workflow with 57 tools ready to use.

Tools Hermes gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Google BigQuery

38 tools

Run Query

Run a SQL query and return results inline (synchronous, bounded by timeout).

Get Query Results

Page through the results of a (possibly async) query job.

Insert Job

Start a query / load / extract / copy job (async).

Get Job

Fetch a job's status and statistics (poll until DONE).

List Jobs

List jobs in a project (filter by state, time range).

Cancel Job

Request cancellation of a running job.

Delete Job

Delete a job's metadata.

List Datasets

List datasets in the project.

Get Dataset

Fetch dataset metadata.

Create Dataset

Create a new dataset.

Update Dataset

Full replace of dataset metadata (PUT).

Patch Dataset

Partial update of dataset metadata (PATCH).

Delete Dataset

Delete a dataset.

List Tables

List tables/views in a dataset.

Get Table

Fetch table metadata/schema.

Create Table

Create a table or view with a schema.

Patch Table

Partial update of a table (add columns, set expiration, etc.).

Update Table

Full replace of table metadata (PUT).

Delete Table

Delete a table or view.

Stream Insert Rows

Streaming insert of JSON rows into a table (real-time append).

List Table Data

Read rows from a table directly (paginated, no SQL).

List Routines

List stored procedures / UDFs / TVFs in a dataset.

Get Routine

Fetch a routine definition.

Create Routine

Create a stored procedure / UDF / TVF.

List Models

List BigQuery ML models in a dataset.

Get Model

Fetch BQML model metadata.

Delete Model

Delete a BQML model.

Get Service Account

Return the BigQuery service account for the project (KMS/transfer grants).

List Projects

List projects the caller can access (for project picker UIs).

Undelete Dataset

Restore a dataset within its time-travel window (datasets.undelete).

Update Routine

Replace a routine's full definition (routines.update, PUT).

Delete Routine

Delete a routine (routines.delete).

Patch Model

Update mutable BQML model metadata (models.patch).

Get Table IAM Policy

Get the IAM policy for a table (tables.getIamPolicy).

Set Table IAM Policy

Set the IAM policy for a table (tables.setIamPolicy).

Test Table IAM Permissions

Test the caller's permissions on a table (tables.testIamPermissions).

List Row Access Policies

List row access policies on a table (rowAccessPolicies.list).

Get Row Access Policy

Get a single row access policy (rowAccessPolicies.get).

Google Sheets

19 tools

Read Sheet Data

Configuration for reading data from a Google Sheet

Write Sheet Data

Configuration for writing data to a Google Sheet

Append Rows to Sheet

Configuration for appending rows to a Google Sheet

Clear Sheet Range

Configuration for clearing values from a range

Create New Spreadsheet

Configuration for creating a new spreadsheet

Fetch Spreadsheet Metadata

Configuration for getting spreadsheet metadata

Read Multiple Sheet Ranges

Configuration for reading multiple ranges at once

Write to Multiple Sheet Ranges

Configuration for writing to multiple ranges at once

Add Spreadsheet Sheet

Configuration for adding a new sheet/tab

Delete Spreadsheet Sheet

Configuration for deleting a sheet/tab

Copy Sheet to Spreadsheet

Configuration for copying a sheet to another spreadsheet

Rename Spreadsheet Sheet

Configuration for renaming a sheet/tab

Duplicate Sheet in Spreadsheet

Configuration for duplicating a sheet within the same spreadsheet

Find and Replace in Spreadsheet

Configuration for find and replace in a spreadsheet

Insert Sheet Rows

Configuration for inserting rows

Delete Sheet Rows

Configuration for deleting rows

Clear Multiple Sheet Ranges

Configuration for clearing multiple ranges at once

Insert Sheet Columns

Configuration for inserting columns

Delete Sheet Columns

Configuration for deleting columns

What you can build

Read a table spec from a Google Sheet and create the matching BigQuery datasets and tables from it.

Work through a cleanup list in a sheet, delete the named BigQuery tables and datasets, then clear the rows it finished.

Keep a spreadsheet inventory of BigQuery routines, appending a row each time the agent creates or deletes one.

Cancel a stuck BigQuery job and write the outcome and timestamp into a tracking sheet.

About Hermes

Hermes is an open agent built on Nous Research’s Hermes models. NoClick runs it hosted and connects your apps to it as tools, so it can do real work across your systems. Wire an integration into the agent and Hermes can use that app’s operations directly while it reasons through a task. It is a strong pick when you want an open-model agent with genuine tool access.

Built on open Hermes models

Capable general reasoning

Flexible, open-model foundation

Hosted with apps wired in as tools