venbrinoDev

I wrote an in-depth research prompt to conduct a GPT-Deep-Research on the Manus topic, seeking to replicate it with currently available open source tools. This is the result:

TLDR: Manus AI Agent Report

Manus is an autonomous AI agent built as a wrapper around foundation models (primarily Claude 3.5/3.7 and Alibaba's Qwen). It operates in a cloud-based virtual computing environment with full access to tools like web browsers, shell commands, and code execution. The system's key innovation is using executable Python code as its action mechanism ("CodeAct" approach), allowing it to perform complex operations autonomously. The architecture consists of an iterative agent loop (analyze → plan → execute → observe), with specialized modules for planning, knowledge retrieval, and memory management. Manus uses file-based memory to track progress and store information across operations. The system can be replicated using open-source components including CodeActAgent (a fine-tuned Mistral model), Docker for sandbox

venbrinoDev

{
  "countries": [
    {
      "name": "Afghanistan",
      "iso3": "AFG",
      "iso2": "AF",
      "phone_code": "93",
      "capital": "Kabul",
      "currency": "AFN",
      "states": [

venbrinoDev

MapNavigationService Utility Class

import 'package:url_launcher/url_launcher.dart';
import 'dart:io';

class MapNavigationService {
  static Future<bool> navigateToGoogleMaps({
    required double destinationLat,
    required double destinationLng,

venbrinoDev

The notification including the sound

import * as FirebaseAdmin from 'firebase-admin';

export class PushNotificationService {
    private readonly logger = new Logger(PushNotificationService.name);

    async sendNotifications(
        tokens: string[] = [],

venbrinoDev

import express, { Request, Response } from "express";
import { Queue, Worker } from "bullmq";
import sharp from "sharp";
import vision from "@google-cloud/vision";
import { Storage } from "@google-cloud/storage";
import multer from "multer";

const app = express();
app.use(express.json());

venbrinoDev

import 'package:flutter/foundation.dart';
import 'package:flutter/material.dart';
import 'package:flutter_local_notifications/flutter_local_notifications.dart';
import 'package:timezone/data/latest_all.dart' as tz;
import 'package:timezone/timezone.dart' as tz;

extension EasyFlutterLocalNotifications on FlutterLocalNotificationsPlugin {
  Future<void> easyInitialize() async {
    tz.initializeTimeZones();
    await initialize(

venbrinoDev

App review - spawn a review only when user meets a threashold

Still Testing

import 'dart:math';

import 'package:flutter_dotenv/flutter_dotenv.dart';
import 'package:in_app_review/in_app_review.dart';
import 'package:zylag/core/data/local_data_source.dart';
import 'package:zylag/core/data/typedefs.dart';

venbrinoDev

Location Service

you can just create an intsance/(you can register this with get_it/ioc contiainer) for easy usage

import 'package:flutter_dotenv/flutter_dotenv.dart';
import 'package:flutter_polyline_points/flutter_polyline_points.dart';
import 'package:geolocator/geolocator.dart';
import 'package:google_maps_flutter/google_maps_flutter.dart';
import 'package:your_project_folder/permission_manager.dart';

venbrinoDev

extension on WidgetTester {
  Future<void> launchApp() async {
    await app.main();
    await pumpAndSettle();
  }

  Future<void> clearState() async {
    await SharedPreferences.getInstance().then((it) => it.clear());
  }

venbrinoDev

1. Make sure to initialize Firebase -
2. Add dependency flutter pub add firebase_messaging
3. Configure your app for ios/macos to receive notification (https://firebase.flutter.dev/docs/messaging/apple-integration/)

Usage

import 'package:firebase_core/firebase_core.dart';
import 'package:firebase_messaging/firebase_messaging.dart';