Introduction
agent-assembly is a governance and security runtime for AI agents. It sits between an agent and the tools, models, and networks it reaches for, evaluates the actions routed to it against policy and budget, and records the outcome in a hash-chained audit trail. It is the open-source core of the AI Agent Assembly platform.
This section is the place to start. It explains what the runtime is and the problem it solves, defines the handful of core concepts the rest of the book assumes, and gives a teaser of the enforcement mechanisms that widen what the runtime can see, depending on how the agent is built and launched.
Read the pages in order:
| Page | What it covers |
|---|---|
| What it is & the problem | What Agent Assembly governs, why ungoverned agent tool-use is risky, and the value proposition. |
| Core concepts | Agents, policies, budgets, audit — the vocabulary used throughout the book. |
| Enforcement mechanisms at a glance | What the SDK, sidecar proxy, and eBPF each see, what deploying more than one buys you, and the gaps that remain. |
When you are ready to run something, jump to the Quick Start. For the security rationale behind the design, read the Security Model; for the crate-level implementation, read Architecture.