Skip to content

Open-source software engineer (anterion.ai)

License

Notifications You must be signed in to change notification settings

Lucas-Strange/anterion

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🤖 Anterion Agent

📖 What is Anterion?

Anterion is an open-source AI software engineer.

Anterion extends the capabilities of SWE-agent to plan and execute open-ended engineering tasks, with a frontend inspired by OpenDevin.

We've equiped Anterion with easy deployment and UI to allow you to fix bugs and prototype ideas at ease.

🏁 Getting Started

🎉 Get on board with Anterion by doing the following! 🎉

Prerequisites

You will need to setup all three components of the system before being able to run it:

1. OpenDevin Setup

To setup OpenDevin, run the following command:

make build-open-devin

2. SWE-agent Setup

Next you will need to setup the SWE-agent.

To start, you will need to cd to the SWE-agent directory, and run the following command:

cd SWE-agent
conda env create -f environment.yml
conda activate swe-agent
cd ..

You will need to create a file called keys.cfg inside of the SWE-agent directory:

OPENAI_API_KEY: '<OPENAI_API_KEY_GOES_HERE>'
ANTHROPIC_API_KEY: '<ANTHROPIC_API_KEY_GOES_HERE>'
GITHUB_TOKEN: '<GITHUB_PERSONAL_ACCESS_TOKEN_GOES_HERE>'

(Optionally) If you want to be able to use Netlify deployments, add the following .env file inside of the SWE-agent directory:

NETLIFY_AUTH_TOKEN="<NETLIFY_AUTH_TOKEN_GOES_HERE>"
NETLIFY_SITE_ID="<NETLIFY_SITE_ID_GOES_HERE>"

Finally, run the following command to setup SWE-agent

make build-swe-agent

3. microservice Setup

Finally you need to setup the microservice, which ties together the OpenDevin frontend and the SWE-agent agent.

First you need to create a .env file in the microservice directory like the following:

OPENAI_API_KEY=<OPENAI_API_KEY_GOES_HERE>
ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY_GOES_HERE>
SWE_AGENT_PATH=<SWE_AGENT_PATH_GOES_HERE>
PYTHON_PATH=<PATH_TO_SWE_AGENT_PYTHON_BINARY_GOES_HERE>

DOCKER_HOST_VOLUME_PATH=<PATH_TO_DOCKER_VOLUME_DIRECTORY_GOES_HERE>
DOCKER_CONTAINER_VOLUME_PATH=/usr/app

SWE_AGENT_PER_INSTANCE_COST_LIMIT=<MAX_USD_PER_AGENT_TASK>
SWE_AGENT_TIMEOUT=25
SWE_AGENT_MODEL_NAME=gpt4

Then, run the following command to build the microservice:

make build-microservice

Finally, within the microservice directory, create a new directory called docker_volume which will be used to contain the agents Docker container will store files within.

cd ./microservice
mkdir docker_volume
cd ..

Usage

To run Anterior, you need to run the frontend and the backend. Run the following command to run both together:

./run.sh

You may have to change permissions for the file first:

chmod +x run.sh

If that isn't working for some reason, run both of them separately:

make run-frontend
make run-backend

🙏 Special Thanks!

We'd like to say thanks to these amazing repos for inspiration!

About

Open-source software engineer (anterion.ai)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 73.2%
  • TypeScript 11.3%
  • Shell 9.0%
  • CSS 1.9%
  • JavaScript 1.7%
  • Makefile 1.6%
  • Other 1.3%