Skip to content

INTEGRATIONS / BRING YOUR OWN AGENTS

Keep your stack. Connect the work.

Choose your agent supervision integration: Python, Node.js, or the HTTP contract. Keep your runtime and add meaningful activity, outcome, and control reporting.

Conceptual illustration of separate agent activity signals held in dark glass panels
.py

For scripts and Python agent workers

Python

Use the Python SDK to report a run lifecycle and meaningful steps. Add checkpoints and guarded actions when you want compatible human control.

See setup instructions →
.js

For JavaScript workers and services

Node.js

Use the Node.js SDK from the process that owns the work. Report outcomes and usage where available, then inspect them in the workspace.

See setup instructions →
POST

For other runtimes and workflow tools

HTTP contract

Connect software that can make outbound HTTPS requests. Implement the documented reporting contract and use an agent-scoped credential.

See setup instructions →

A SMALL, DELIBERATE INTEGRATION

Start with reporting.
Add control at real boundaries.

01Your agents

Local · cloud · scheduled

02Toolcaise

Activity · incidents · outcomes

03Your decision

Review · approve · investigate

04Your runner

Handle the decision at a checkpoint

Report a heartbeat, an actual run, and a useful outcome. A standalone heartbeat confirms contact but does not instrument the rest of your workflow. Docker and cloud workloads can use the same SDK or HTTP paths inside the environment you already operate.

No model-provider key or inbound port is required. Keep agent credentials in secure runner configuration, and send only the operational metadata needed for supervision.

Framework compatibility depends on your integration.

An agent built with a framework can report through these paths when you can instrument its code or workflow. This is not a claim of a native connector to every agent framework. Controls require compatible checkpoints; monitoring alone does not add them.

Explore the separate Toolcaise Connect preview →

START WITH ONE WORKFLOW

Put your next run
under supervision.

Connect the agent you already run. Build confidence from the work you can actually review.