Developers

Build with a runtime that treats consequence as a first-class concern

MAPLE gives developers packageable agents, model-neutral inference, explicit capabilities, commitment gating, and replayable provenance without inventing those control surfaces from scratch.

Fastest Path

Clone the repo and run the demo

git clone https://github.com/mapleaiorg/maple.git
cd maple
ollama serve &
ollama pull llama3.2
cargo run -p maple-demo

Install and quickstart

Use the docs for a clean install path and a 5-minute first run.

Open getting started

Build your first agent

Scaffold a package, define a Maplefile, and run a TODO agent with Guard policy.

Open tutorial

Use the API and SDKs

Reference the REST surface and Rust, TypeScript, and Python clients.

Open API docs

Core Semantics

Three rules to design around

Cognition is advisory

Model output drafts intent. It does not grant execution authority.

Capabilities are explicit

Tool access begins at zero and is granted narrowly through Guard and package contracts.

Receipts matter

Every meaningful effect should remain inspectable through provenance history.

Need implementation support for your first governed workflow?

MapleAI Intelligence Inc. can help package the first agent, design capability boundaries, and shape the production rollout path.

Talk to Developer Team Browse Docs