daily

GitHub All Languages Trending

The latest build: 2024-05-29Source of data: GitHubTrendingRSS

Fully open source, End to End Encrypted alternative to Google Photos and Apple Photos


Fully open source end-to-end encrypted photos, authenticators and more.

Ente

Ente is a service that provides a fully open source, end-to-end encrypted platform for you to store your data in the cloud without needing to trust the service provider. On top of this platform, we have built two apps so far: Ente Photos (an alternative to Apple and Google Photos) and Ente Auth (a 2FA alternative to the deprecated Authy).

This monorepo contains all our source code - the client apps (iOS / Android / F-Droid / Web / Linux / macOS / Windows) for both the products (and more planned future ones!), and the server that powers them.

Our source code and cryptography have been externally audited by Cure53 (a German cybersecurity firm, arguably the world's best), Symbolic Software (French cryptography experts) and Fallible (an Indian penetration testing firm).

Learn more at ente.io.


Ente Photos

Screenshots of Ente Photos

Our flagship product. 3x data replication. On device machine learning. Cross platform. Private sharing. Collaborative albums. Family plans. Easy import, easier export. Background uploads. The list goes on. And of course, all of this, while being fully end-to-end encrypted.

Ente Photos is a paid service, but we offer a free trial. You can also clone this repository and choose to self host.



Ente Auth

Screenshots of Ente Photos

Our labour of love. Two years ago, while building Ente Photos, we realized that there was no open source end-to-end encrypted authenticator app. We already had the building blocks, so we built one.

Ente Auth is currently free. If in the future we convert this to a paid service, existing users will be grandfathered in.



Contributing

Want to get aboard the Ente hype train? Welcome along! Don't hesitate if you're not a developer, there are many other important ways in which you can contribute.

Support

We are never more than an email away. For the various ways to ask for help, please see our support guide.

Community

Ente's Mascot, Ducky,inviting people to Ente's source code repository

Please visit our community page for all the ways to connect with the community.

DiscordEnte's Blog RSS

Twitter   Mastodon


Security

If you believe you have found a security vulnerability, please responsibly disclose it by emailing [email protected] or using this link instead of opening a public issue. We will investigate all legitimate reports. To know more, please see our security policy.

Large Action Model framework to develop AI Web Agents


StargazersIssuesForksContributors


LaVague Logo

Welcome to LaVague

Join our Discord server!Docs

A Large Action Model framework for developing AI Web Agents

What is LaVague?

LaVague is an open-source Large Action Model framework to develop AI Web Agents.

Our web agents take an objective, such as "Print installation steps for Hugging Face's Diffusers library" and performs the required actions to achieve this goal by leveraging our two core components:

  • A World Model that takes an objective and the current state (aka the current web page) and turns that into instructions
  • An Action Engine which compiles these instructions into action code, e.g. Selenium or Playwright & execute them

Getting Started

Demo

Here is an example of how LaVague can take multiple steps to achieve the objective of "Go on the quicktour of PEFT":

Demo for agent

Hands-on

You can do this with the following steps:

  1. Download LaVague with:
pip install lavague
  1. Use our framework to build a Web Agent and implement the objective:
from lavague.core import WorldModel, ActionEngine, PythonEnginefrom lavague.core.agents import WebAgentfrom lavague.drivers.selenium import SeleniumDriverselenium_driver = SeleniumDriver(headless=False)world_model = WorldModel()action_engine = ActionEngine(selenium_driver)python_engine = PythonEngine()agent = WebAgent(world_model, action_engine, python_engine)agent.get("https://huggingface.co/docs")agent.run("Go on the quicktour of PEFT")

For more information on this example and how to use LaVague, see our quick-tour.

Note, these examples use our default OpenAI API configuration and you will need to set the OPENAI_API_KEY variable in your local environment with a valid API key for these to work.

For an end-to-end example of LaVague in a Google Colab, see our quick-tour notebook

Contributing

We would love your help and support on our quest to build a robust and reliable Large Action Model for web automation.

To avoid having multiple people working on the same things & being unable to merge your work, we have outlined the following contribution process:

  1. We outline tasks on our backlog: we recommend you check out issues with the help-wanted labels & good first issue labels
  2. If you are interested in working on one of these tasks, comment on the issue!
  3. We will discuss with you and assign you the task with a community assigned label
  4. We will then be available to discuss this task with you
  5. You should submit your work as a PR
  6. We will review & merge your code or request changes/give feedback

Please check out our contributing guide for a more detailed guide.

If you want to ask questions, contribute, or have proposals, please come on our Discord to chat!

Roadmap

TO keep up to date with our project backlog here.

Security warning

Note, this project executes LLM-generated code using exec. This is not considered a safe practice. We therefore recommend taking extra care when using LaVague and running LaVague in a sandboxed environment!

Data collection

We want to build a dataset that can be used by the AI community to build better Large Action Models for better Web Agents. You can see our work so far on building community datasets on our BigAction HuggingFace page.

This is why LaVague collects the following user data telemetry by default:

  • Version of LaVague installed
  • Code generated for each web action step
  • LLM used (i.e GPT4)
  • Multi modal LLM used (i.e GPT4)
  • Randomly generated anonymous user ID
  • Whether you are using a CLI command or our library directly
  • The instruction used/generated
  • The objective used (if you are using the agent)
  • The chain of thoughts (if you are using the agent)
  • The interaction zone on the page (bounding box)
  • The viewport size of your browser
  • The URL you performed an action on
  • Whether the action failed or succeeded
  • Error message, where relevant
  • The source nodes (chunks of HTML code retrieved from the web page to perform this action)

Turn off all telemetry

If you want to turn off all telemetry, you can set the TELEMETRY_VAR environment variable to "NONE".

If you are running LaVague locally in a Linux environment, you can persistently set this variable for your environment with the following steps:

  1. Add TELEMETRY_VAR="NONE" to your ~/.bashrc, ~/.bash_profile, or ~/.profile file (which file you have depends on your shell and its configuration)
  2. Use `source ~/.bashrc (or .bash_profile or .profile) to apply your modifications without having to log out and back in

In a notebook cell, you can use:

import osos.environ['TELEMETRY_VAR'] = "NONE"

Bot that mines coins in HamsterKombat


img1

README in english available here

- (tap, energy, charge)
tdata / pyrogram .session / telethon .session

API_ID / API_HASH , Telegram ( - Android)
MIN_AVAILABLE_ENERGY , (. 100)
SLEEP_BY_MIN_ENERGY(. 200)
ADD_TAPS_ON_TURBO(. 2500)
AUTO_UPGRADE(True / False)
MAX_LEVEL(. 20)
APPLY_DAILY_ENERGY(True / False)
APPLY_DAILY_TURBO(True / False)
RANDOM_CLICKS_COUNT(. [50,200])
SLEEP_BETWEEN_TAP(. [10,25])
USE_PROXY_FROM_FILE- bot/config/proxies.txt(True / False)

  1. Windows, INSTALL.bat.
  2. START.bat ( : python main.py).

, , :

API

  1. my.telegram.org , .
  2. "API development tools" .
  3. API_IDAPI_HASH.env, .

:

~ >>> git clone https://github.com/shamhi/HamsterKombatBot.git ~ >>> cd HamsterKombatBot# Linux~/HamsterKombatBot >>> python3 -m venv venv~/HamsterKombatBot >>> source venv/bin/activate~/HamsterKombatBot >>> pip3 install -r requirements.txt~/HamsterKombatBot >>> cp .env-example .env~/HamsterKombatBot >>> nano .env # API_ID API_HASH , ~/HamsterKombatBot >>> python3 main.py# Windows~/HamsterKombatBot >>> python -m venv venv~/HamsterKombatBot >>> venv\Scripts\activate~/HamsterKombatBot >>> pip install -r requirements.txt~/HamsterKombatBot >>> copy .env-example .env~/HamsterKombatBot >>> # API_ID API_HASH, ~/HamsterKombatBot >>> python main.py

, :

~/HamsterKombatBot >>> python3 main.py --action (1/2)# ~/HamsterKombatBot >>> python3 main.py -a (1/2)# 1 - # 2 -