OpenAPI graph

SkillDev tools

OpenAPI front example; a graph whose step turns an OpenAPI operation into a sealed tool result.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the OpenAPI graph skill

What this skill tells your AI

The instructions your AI receives, as published by runxhq/runx in examples/openapi-graph/SKILL.md and read by ahel’s review.

A single-step graph that drives the OpenAPI external-adapter sub-skill. The runtime routes the graph step's external-adapter source through the source-adapter registry to the external-adapter executor, which spawns the declared adapter process. The adapter resolves an OpenAPI operation into a concrete HTTP request and the runtime seals it. Its manifest declares a required network scope because the adapter performs the outbound fetch.

This is the concrete proof that the core runs from other specs, not just MCP. Run examples/openapi-graph/run.sh to start the local fixture endpoint and fail hard unless the graph state proves the GET executed and returned the expected pet payload, and the receipt directory contains a signed runx.receipt.v1.

The inline harness case expects that fixture endpoint to be running. Use run.sh for the hermetic demo entrypoint; bare runx harness examples/openapi-graph is only useful after starting server.mjs separately.

Signals

GitHub stars
87
Forks
101
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
openapi-graph
Source
github.com/runxhq/runx