Skip to content

rohanarun/Open-Agent-Studio

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

76 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Open Agent Studio

Open Agent Studio is the first cross platform desktop application built to enable Agentic Process Automation as an open-source alternative and replacement for UIpath and all other RPA tools today.

Download for Windows and Mac at https://openagent.studio.

We founded Cheat Layer during the pandemic to help people who had lost their jobs and businesses rebuild online using GPT-3. We personally helped hundreds pro bono before turning to AI for help.

In August 2021, we were the first startup to get approved by openAI to sell GPT-3 for automation. We were the first to publish our framework for agents, Project Atlas, in July 2022.

Businesses today are threatening to fire employees and replace them with AI. We believe within 2 years, the AI necessary to generate most of those businesses will be a commodity.

In a future where the AI in your pocket can generate custom, secure, and free versions of all the most expensive business software, we believe there'll be a level playing field that removes the barrier to build these businesses. More small businesses will build competitive brands through personal relationships, better quality service, and network effects through unique data. We invite you to join us in building this future together faster.

This is an older public version of our internal private repo which will be updated in the coming days with the latest updates to Open Agent Studio 7.0.0 whch can be downloaded at openagent.studio now.

Agentic Process Automation

Generalized Agents framework image

Semantic Targets

Semantic targets distils the underlying intent of a target to english, so they still work even if services completely change their designs. This enables building robust, future-proof, agents.

Semantic targets can be dynamic or robust based on how strict the language is.

Semantic Triggers

Semantic Triggers

Reasoning Based Targets

Reasoning Based Targets

Windows Instructions

Check docs.cheatlayer.com for more details.

Install Python 3.10 You need to install python 3.10 to enable agents to install any arbitrary python library when solving general problems.

You can get Python 3.10 from the Windows Store.

Python 3.1 for Cheat Layer Desktop Windows Store Python 3.1

Step 1: Download the latest Desktop Version

Download the Software: Visit the official Cheat Layer website and download the latest version of Cheat Layer Desktop.

To get the latest version of Cheat Layer Desktop. Navigate to the cheat layer web page, click on the option for interactive onboarding, and then proceed to download Cheat Layer Desktop.

Step 2: Download and Decompress

Run the Installer: Locate the downloaded file and decompress the file.

Extracting the compressed files from .zip file Extracting Cheat Layer Desktop Follow the on-screen instructions to finish the decompression process.

Step 3: Launch Cheat Layer Desktop

Initiating Cheat Layer Desktop for the first time involves navigating through Windows security prompts. Upon launching the application, Windows may display security warnings. Users should select "More info".

Then select the option "Run anyway"

Then, follow this quick start guide to dive deeper into Cheat Layer Desktop:

Update: Epic breakthrough! We just cracked unlimited agents and executions!

Contributions:

Currently we still need to open source the backend and Chrome Extension to be able to run everything locally, but if you are interested in contributing please email me at rohan@cheatlayer.com and I can get you set up with free access while we work on publishing everything.

We need help with evals for generalized stretch goals to push the limits of the state machine and Loom video to agents, and to improve the testing loop. We strongly believe the testing loop to be the path to the 'holy grail' for open-ended generalized tasks.

Road Map:

  1. Open agent cloud
  2. Loom video to agent in Open Agent Cloud
  3. Evals for generalized agents
  4. Improve testing loop to reach generalized agents with this same scaffolding on the shoulders of the next generations of models.

Thansk!

Star History

Star History Chart