One way into the SDK
Nothing calls the agent SDK directly. A second path would mean a cost ledger that undercounts, approval gates that never appear, and per-role tool tables that turn into advice.
17 / AI agent framework · solo · internal tool
A framework for letting an AI agent work for a long stretch without deciding the big things itself: at each important point it stops and waits for a person. Long-running agents burn money, drift, or do things nobody allowed, so the control sits in the framework and does not rely on the model behaving. NYX built it for its own use and does not sell it.

Limits are tripped by counters, never by what the agent says about itself.
Nothing calls the agent SDK directly. A second path would mean a cost ledger that undercounts, approval gates that never appear, and per-role tool tables that turn into advice.
Gates are opened by framework code around the loop, so there is no gate tool a manipulated model could reach. The 10 kinds are rows in one table. A late gate gets a louder reminder, and nothing ever decides for the person.
The sandbox has network while dependencies install and none before third-party code runs. That order lives inside the module, so it is a property of the system and not a habit of the caller. An agent with a sandbox has no outside credentials, and the reverse.
Assumptions, cost and time each have a ceiling, and each is a counter. On reaching one, the run stops first and opens a gate second. Nothing dead gets restarted automatically.
Build a product together, distribute one that exists, commission software, or join in — write a few lines and NYX will get back to you.
Send an invitation →