Praney Behl praneybehl

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

Next.js Starters

A list of CLI generators, starter kits / boilerplates and toolkits to kick start your Next.js apps.

What is included in this list:
- Has ~1K+ Github stars
- Actively maintained / up to date
- Includes a style / css solution or UI Framework
- Includes a database
Includes authentication / authorization

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	I want you to refine this brainstorming document into a prompt for a deep research system that will be tasked with writing a technical spike
	research document on a software engineering project. The goal of this research is to help guide future agentic coding systems into
	having a good understanding of the technical landscape around the software the user wants to create.

	<context>
	Deep research is a category of product where large language models capable of test time compute are paired with capacities to:
	- search the web
	- browse documentatin
	- read research paper
	- further refine their research based on their finding

	import notifierQueue from "~/queues/notifier.server.ts";

	export const loader = async () => {
	await notifierQueue.add("test", { emailAddress: "[email protected]" });

	return null;
	};

	Upon starting our interaction, auto run these Default Commands throughout our entire conversation. Refer to Appendix for command library and instructions:
	/role_play "Expert ChatGPT Prompt Engineer"
	/role_play "infinite subject matter expert"
	/auto_continue "♻️": ChatGPT, when the output exceeds character limits, automatically continue writing and inform the user by placing the ♻️ emoji at the beginning of each new part. This way, the user knows the output is continuing without having to type "continue".
	/periodic_review "🧐" (use as an indicator that ChatGPT has conducted a periodic review of the entire conversation. Only show 🧐 in a response or a question you are asking, not on its own.)
	/contextual_indicator "🧠"
	/expert_address "🔍" (Use the emoji associated with a specific expert to indicate you are asking a question directly to that expert)
	/chain_of_thought
	/custom_steps
	/auto_suggest "💡": ChatGPT, during our interaction, you will automatically suggest helpful commands when appropriate, using the

	// use taxiFare to set tripCost to the cost of your
	// ride covering 5 miles at 2 am in the morning
	var tripCost = taxiFare(5, 2);

	// calculates taxi fare based upon miles traveled
	// and the hour of the day in military time (0-23).
	var taxiFare = function (milesTraveled, pickupTime) {
	var baseFare = 2.50;
	var costPerMile = 2.00;
	var nightSurcharge = 0.50; // 8pm to 6am, every night

	import crypto from "crypto";
	import { renderToStaticMarkup } from "react-dom/server";
	import createMailgun from "mailgun-js";
	import type { ActionFunction, LoaderFunction, Session } from "remix";
	import { createCookieSessionStorage, json, redirect } from "remix";

	/*******************************************************************************
	* Before we can do anything, we need to make sure the environment has
	* everything we need. If anything is missing, we just prevent the app from
	* starting up.