Right now reasoning shows up as its own nodes in the graph alongside the tool calls so you can follow the full chain what claude was thinking then what it did. Still early and there's room to improve how it's presented, but the core is there.
Happy to answer any questions about the implementation. Built in Go - the OpenAPI Scanner was the most challenging part, it analyzes source code across multiple languages to auto-generate OpenAPI 3.1 specs. The headless mode was built specifically for CI/CD pipelines so you can run octrafic test non-interactively. Supports local LLMs via Ollama and llama.cpp if you don't want data leaving your machine.
Hi - I built Octrafic, an open-source CLI for AI-assisted API testing and exploration.
Instead of writing test scripts, you can describe what you want to verify in natural language and Octrafic generates requests and validations based on your API spec (OpenAPI/Swagger, Postman Collections, GraphQL, etc.).
It’s BYOK: you plug in your own AI provider key (Anthropic / OpenRouter / OpenAI), and the CLI runs locally.