docs
Documentation hub.
Full API reference and concept deep dives live in the repo's documentation/ tree. Here's the
orientation; the source of truth is GitHub.
Quickstart
- /install — one pubspec line + a 30-second hello agent.
-
example/quickstarts (GitHub) ↗
— five runnable Flutter apps:
hello_agent,multi_tool,on_device,voice,mobile_automation.
Concepts
API reference (in repo)
The Dartdoc-generated reference lives on pub.dev:
Deeper reading on the marketing site
- Why mobile-native — the founding argument.
- On-device routing — providers +
ModelRoute.preferOnDevice. - Compare — vs Claude SDK, OpenAI Agents SDK, Mastra, LangChain.
- Blog — long-form articles on individual primitives.
Snippets you'll re-use
dependencies:
agentlib: ^1.1.0 final agent = AgentSpec(
name: 'helper',
instructions: 'You are a helpful mobile assistant.',
model: AnthropicProvider(apiKey: const String.fromEnvironment('ANTHROPIC_API_KEY')),
);
final run = Runner.runStreamed(
agent.toRunConfig(vfs: Vfs(), threadId: 'main'),
input: 'What time is it?',
);
await for (final e in run.events) {
if (e is TextDelta) print(e.delta);
} For AI search
The /llms.txt file is a curated index of this site for LLM crawlers. The /llms-full.txt file is the full content dump — README + all articles concatenated.