PtcRunner

A runtime for Code Mode agents

Build AI agents that are bounded in what they can do, easy to change, observable in operation, and designed to improve from evidence.

Today, agents usually choose between two extremes. They either call tools one at a time, paying a model round trip and adding context for every step, or use a full coding environment and an external sandbox for more complex work. PtcRunner provides the missing middle: it lets a model write a small, bounded program that calls several approved tools, processes their results, and returns only what matters.

You normally do not write that program. You provide the task, model, approved tools, data, limits, and agent components. The model writes the mission program; PtcRunner executes it and records what happened.

Authority only narrows. A full-width box labelled OPERATOR, ptc-host.json, holding credentials, endpoints, and outer ceilings. An arrow down to a narrower box labelled AUTHOR, ptc.json, holding aliases, missions, and limits, captioned 'selects from, never adds to'. A second arrow, captioned 'splits, never merges', leads to two separated boxes: WORKFLOW, trusted policy, holds the model; and MISSION, the model-written program, holds the tools.
Every layer selects from the one above it and can only narrow. Selecting a library installs its dependency closure — it does not grant tool authority, so swapping the agent loop changes policy, not power.

0.x, under active development. Breaking changes are expected. The public one-command installer and published container image are not available yet — today you build the standalone executable locally, run the locally built container, or use the Hex package. The availability table states exactly where each route stands.

JSON Schemas

Schema reference → The stable URLs for the project, application, host, and command-envelope schemas. Point your editor at one to get completion and validation while authoring.

Links