renschni

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

jlia0

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

thomwolf

import os; import psutil; import timeit
from datasets import load_dataset

mem_before = psutil.Process(os.getpid()).memory_info().rss >> 20
wiki = load_dataset("wikipedia", "20200501.en", split='train')
mem_after = psutil.Process(os.getpid()).memory_info().rss >> 20
print(f"RAM memory used: {(mem_after - mem_before)} MB")

s = """batch_size = 1000
for i in range(0, len(wiki), batch_size):

egrefen

# Based on the code in https://github.com/tristandeleu/pytorch-meta/tree/master/examples/maml
# Basically, we only use the dataset loaders/helpers from TorchMeta and replace usage of MetaModules
# with normal pytorch nn.Modules, letting higher deal with making the inner loop unrollable and the
# optimizers differentiable. This makes it easier to use another optimizer than SGD, or any arbitrary
# third-party model, when doing MAML using this codebase.

import os
import torch
import torch.nn as nn
import torch.nn.functional as F

karamanbk

cezaraugusto

For troubleshooting, two things to first try:

run `git config --global gpg.program gpg2`, to make sure git uses gpg2 and not gpg
run `echo "test" | gpg2 --clearsign`, to make sure gpg2 itself is working
If that all looks all right, one next thing to try:

run `brew install pinentry` to ensure you have a good tool installed for passphrase entry
If after that install and you re-try git commit and still get the "failed to sign the data" error:

run `gpgconf --kill gpg-agent` to kill any running agent that might be hung

aparrish

suriyadeepan

from bs4 import BeautifulSoup
import requests

start_url = 'https://en.wikipedia.org/wiki/Transhumanism'
domain = 'https://en.wikipedia.org'

''' get soup '''
def get_soup(url):
    # get contents from url
    content = requests.get(url).content

abhin4v

module Calc
( Expr(..)
, parse
, calculate
) where

import Control.Applicative
import Parser

data Expr = Add Expr Expr

kidpixo

Warning This is SEVERELY outdated, the current jupyter version is > 6.X, please refer to your current jupyter notebook installation!

Disclaimer : I just copied those shortcuts from Jupyter Menú > Help > Keyboard Shortcuts, I didn't wrote them myself.

Check your current shortcuts in your Help, shortcuts coule have been modified by extensions or your past self.

Toc

Keyboard shortcuts