OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Cockpit Agent Sim

Cockpit Agent Sim is a TypeScript framework and simulation project for building smart-cockpit agent demos. It combines an agent runtime, simulated vehicle signals, tools, memory, a display-oriented HMI and text-to-speech, with skill-based scenario extensions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cockpit Agent Sim — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it to explore and demonstrate smart-cockpit agent behavior in a simulated setup, especially when you want a starting framework for tools, memory and a cockpit display rather than building each demo from scratch.

Who it is for

  • Developers prototyping conversational smart-cockpit agents.
  • Teams exploring simulated vehicle-control flows and cockpit interfaces.
  • Builders creating skills that combine tools, memory and vehicle-signal scenarios.

Documented uses

  • Prototype an agent that interprets driver requests and uses vehicle-control tools.
  • Simulate cockpit scenarios using vehicle signals and injected vehicle state.
  • Create a conversational interface with a separate display-oriented cockpit screen.
  • Extend a demo with cockpit scenarios packaged as skills.
Before you choose

Requirements & limits

The README documents local setup with npm and an environment file. It says an OpenRouter key can start the project and that navigation and maps require an Amap key. Text entry through the control panel substitutes for speech recognition.

  • It is an MIT-licensed TypeScript project with a public GitHub repository.
  • The project is described as having no backend; the development server includes a forwarding proxy for third-party services.
  • The README describes permission levels and confirmation prompts for some vehicle-control actions.
  • Speech recognition is not included; text is entered through the control panel.
  • Navigation and maps need an Amap key, while other integrations may use third-party services.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the local development demo

Install the project, configure its documented model key and start the local development server.

Before you start

  • Node.js and npm, as implied by the documented npm commands.
  • An OpenRouter API key, described in the README as sufficient to start.
  • An Amap key if using navigation or map features.

Steps

  1. Run the command below in the project directory.

    Documented command
    npm install

  2. Copy .env.local.example to .env.local and add the required key or keys, following the comments in that file.

  3. Run the command below and open the displayed local address; the README gives http://localhost:5173.

    Documented command
    npm run dev

  4. Enter text through the control panel, since the project does not include speech recognition.

Expected outcome

A locally running smart-cockpit demo that accepts text input through its control panel.

Guide limitations

  • The README presents the project as a demo foundation, not a production vehicle system.
  • Navigation and map features require an Amap key.
  • Model capability affects tool invocation; the README warns that some lightweight models may claim actions without calling tools.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
24 October 2026
Original website title
yancent-dao/cockpit-agent-sim · Official homepage title · retained in its source language
How we review sourcesSuggest a correction