Developer Portal

Building with an AI coding assistant?

All of this documentation is published as a single plain-text file — every page, both the TypeScript and Python form of every code sample. Give your assistant the URL instead of pointing it at these pages one at a time.

Start here

Two runnable starter apps — same insurance-claims agent, your choice of language.

TypeScript starter

TypeScriptNode ≥ 18Anthropic

aitrust-agent-starter — browser chat, Claude Vision damage assessment, settlement PDF, in-browser signing. No KOBIL SDK yet.

View the repo →

Python starter

PythonFastAPIAnthropic

aitrust-agent-starter-python — the same app on FastAPI + reportlab. Identical flow and API, shared web UI.

View the repo →

What the SDK adds to a tool call

Register your tools once; every call the model makes runs through one guarded pipeline.

  1. 1token acquire mTLS, no secrets
    in agent memory
  2. 2FGA check OpenFGA
    policy decides
  3. 3CIBA approval human says
    yes on phone
  4. 4execute your tool
    code runs
  5. 5audit tamper-evident
    trail
Step 1

Identity

Every agent has a verifiable platform identity; tokens are acquired over mTLS and never live in agent memory.

Steps 2–3

Authorization & approval

OpenFGA decides which tools may run; sensitive actions require a human approval on their phone via CIBA.

Step 5

Audit

Every tool call is written to a tamper-evident audit trail.