TL;DR: we just shipped the Hatchet CLI, which you can install via:
This lets you interact with Hatchet from your terminal, and is particularly useful for coding agents like Claude Code and Cursor. You can find the full documentation for the CLI here.
A frequent ask from Hatchet users has been better support for coding agents, like Claude Code and Cursor, and in particular support for an MCP integration or skills. The new CLI now comes bundled with a handful of skills that early users have found particularly useful, like debugging or replaying runs. This can be installed into your project via:
You can also install an MCP which provides helpful context for coding agents, like how to use the SDKs to write tasks and workflows. This can be installed via:
For more information, see here: https://docs.hatchet.run/home/coding-agents
The CLI provides a bunch of new commands for interacting with runs. For example, you can list all recent failed runs with:
You can also replay a run with:
Or a batch of runs based on filters:
There much more, like listing logs, child runs, cancellations, and status checks. Run hatchet runs -h for the full set of commands.
The CLI comes with functionality for running a worker locally with hot reload, as well as triggering tasks. To run a worker locally, you can run:
This will start a local worker which automatically connects to your Hatchet account, and reloads whenever you make changes to your code. See docs for more details: https://docs.hatchet.run/cli/running-workers-locally.
We're also shipping a full terminal user interface (TUI) for Hatchet, which you can access by running:
This TUI provides a way to visualize your tasks and workflow runs from the terminal, without needing to switch over to the web UI. It's particularly useful for users who are developing Hatchet tasks and durable workflows in their IDE:
The CLI also comes with additional commands for managing your Hatchet account and resources, like:
hatchet workflows for listing and managing your workflowshatchet scheduled for listing and managing scheduled taskshatchet cron to manage cron jobshatchet rate-limits to view your current (user-side) rate limits