Run a self-verifying desktop AI agent on your own machine: a 10-minute quickstart

说明与用途

OpenAmer 是一个本地 AI 代理，能够在桌面上执行操作，并在每个操作之前写入收据，从而实现对其行为的事后验证。

问题

Deploy a local AI agent that can act on desktop windows while providing verifiable receipts of its actions.

结果

The agent can autonomously perform desktop tasks, logs each action with a pre-execution receipt, and provides a durable record that can be audited after the fact.

工作流

• Install OpenAmer via shell or PowerShell script
• Run openamer setup to configure model provider and optional OAuth
• Use openamer asi think/learn/remember to invoke reasoning, learning, and memory subsystems
• Drive desktop by controlling a persistent Chrome profile or native windows via DevTools protocol
• Observe that the agent writes receipts to an outcome ledger before performing actions
• Verify receipts to confirm actions succeeded or failed
• Optionally run multiple instances to explore A2A Global Mesh features

证据

OpenAmer is an open-source (Apache-2.0), Windows-first personal agent.

来源

Every action it takes is logged with a pass/fail you can check afterwards.

来源

The agent writes receipts before the side effect, so an already-landed action becomes a no-op instead of a double action.

来源