Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

AI Agent Assembly Documentation

core python-sdk node-sdk go-sdk license

Quick links to each component, its current version, and its license. Every version badge reads the latest published version live — core and Go from GitHub, Python from PyPI, Node from npm’s rc dist-tag — so they stay current with no manual updates. The project is in release candidate (v0.0.1-rc).

AI Agent Assembly is a governance layer for AI agents. It sits between your agents and the outside world and does three things:

  • Enforces policy — decides, before each action runs, whether an agent is allowed to call a tool, reach a domain, or spend more budget.
  • Tracks cost — meters token and dollar spend per team and blocks agents that exceed their budget.
  • Intercepts unsafe actions — catches risky calls (and bypass attempts) at the SDK, network, and kernel levels.

It works across your whole fleet of agents and does not require you to rewrite your existing agent code.

Who this documentation is for

This site is for teams, security engineers, and operators evaluating or running AI Agent Assembly for production adoption.

If you are a developer who wants to contribute or integrate at the code level, see the open-source documentation instead.

Find what you need

Pick the page that matches what you are trying to do.

I want to…Go to
Govern my first agent in a few minutesQuick start (SaaS)
Understand the security posture and threat modelSecurity model
Compare AI Agent Assembly to other toolsWhy AI Agent Assembly?
Know what is open source vs. paidOpen core boundary
Set up SSO, SCIM, regions, and billingCloud deployment
Look up a policy field or write a policyPolicy reference

SDKs & components

This hub is the central entry point for AI Agent Assembly documentation. To instrument your agents, you install the SDK for your language — each one ships its own documentation site. Use the table below to go to the SDK that matches your codebase (Python, Node/TypeScript, or Go), or to Arena, the cross-framework governance trial ground.

Every module’s docs are aggregated into this hub under a stable subpath (/core/, /python-sdk/, /node-sdk/, /go-sdk/, /arena/), so you can read and search all of them from one place. The standalone, per-version sites remain available for release-specific (mike / Docusaurus / Hugo channel) browsing.

Runnable examples

Prefer learning by running code? The agent-assembly-examples repo collects small, framework-specific Agent Assembly examples for Python, Node.js/TypeScript, Go, policy enforcement, approvals, audit, trace, and runtime workflows. Clone it and run an example end to end to see governance in action before instrumenting your own agents.

The three-layer interception model

AI Agent Assembly enforces governance through three layers. You can deploy them independently, and each one catches what the layer above it might miss:

  1. SDK layer (in-process) — the language SDK wraps your agent calls and applies allow/deny decisions before any network request leaves the process. Fastest path, but requires you to adopt the SDK.
  2. Sidecar proxy (aa-proxy) — intercepts outbound HTTPS using a per-host CA, so it can govern agents that do not use the SDK. No code changes required.
  3. eBPF sensor (aa-ebpf) — kernel-level hooks that watch SSL libraries and process syscalls to catch bypass attempts at the OS level. Linux only.

All three layers report to the gateway, which evaluates policy and tracks per-team budgets.

Next step Continue to the Quick start →

Instrument a LangChain agent in under five minutes.


Last reviewed: 2026-06-27 — AI Agent Assembly Team


Last updated: 2026-07-11 by AI Agent Assembly Team