Token-efficient
An agent is ~28% of the tokens of the equivalent JSON-schema + SDK boilerplate it replaces — cheaper to write, read, and generate.
Token-Oriented Agentic Development
Agents as data.
Compiled to types.
Write an AI agent as a tiny, declarative .agent file in a
token-oriented syntax derived from
TOON. The toac compiler turns it into readable, fully-typed
TypeScript that runs on Claude — minimal enough that humans
and LLMs can author it.
/toʊd/ — you write what the agent is; the compiler writes how.
The whole idea, in one screen
researcher.agent
researcher.ts generated
Why TOAD
A framework, not a wrapper.
Schema-explicit
[N] lengths and {field} headers hand a
model the structure up front, so it can author agents reliably.
Typed end-to-end
inputs, outputs, and tools
become real TypeScript types. Misuse is a compile error.
Logic in plain TS
Tool bodies live in a co-located .tools.ts — the
escape hatch for anything the declarative layer shouldn't do.
Built on real TOON
Structural parsing is delegated to the spec-conformant
@toon-format/toon decoder. No bespoke parser.
Compile-first
The output is readable TypeScript you can read, diff, and debug — not an opaque runtime. The emitted code is the docs.
Community
It's open source — come build it.
TOAD is MIT-licensed and early. Star it, file an issue, or send a PR — the compiler, runtime, language features, and docs are all fair game.