A simple autocomplete agent that uses gen AI to fill out forms
  • TypeScript 86.4%
  • Dockerfile 7%
  • Makefile 6.6%
Find a file
2026-02-17 22:30:43 -05:00
src fixed incorrect error handling 2026-02-17 22:27:14 -05:00
.gitignore update gitignore to allow example files 2026-02-16 23:25:10 -05:00
docker-compose.yaml containerization, base setup 2026-02-16 22:59:04 -05:00
Dockerfile containerization, base setup 2026-02-16 22:59:04 -05:00
example.env added example files 2026-02-16 23:25:51 -05:00
LICENSE Initial commit 2026-02-15 17:10:53 -05:00
Makefile containerization, base setup 2026-02-16 22:59:04 -05:00
package-lock.json containerization, base setup 2026-02-16 22:59:04 -05:00
package.json containerization, base setup 2026-02-16 22:59:04 -05:00
README.md fix spelling 2026-02-17 22:30:43 -05:00
supervisord.conf containerization, base setup 2026-02-16 22:59:04 -05:00
tsconfig.json containerization, base setup 2026-02-16 22:59:04 -05:00

Autocomplete Agent 🤖

An AI agent designed to automate form filling using generative AI.

🚀 Getting Started

Follow these steps to configure, build, and run the agent.

1. Configure Environment Variables

You need to set up your Google API key.

  1. Get your API Key: Obtain a key from Google AI Studio: https://aistudio.google.com/apikey

  2. Create the .env file: In the base directory of the project, duplicate example.env and rename it to .env.

  3. Add your Key: Open your new .env file and paste your API key:

2. Configure Form Data

Define the data that the agent will use to autofill forms.

  1. Create the data file: Navigate to the data/ folder.
  2. Match the template: Create a new file named forms.json using data/example.forms.json as your template.
  3. Input your data: Fill forms.json with the specific information you want the agent to use.

🛠️ Usage

Build the Agent

Run the following command to build the project:

make build

Start the container

Run the following command to start the container:

make up

Supervise the agent

Once the build is complete, go to this URL to supervise the agent: http://localhost:6080/

Run the agent

With the browser view open, execute the run command in your terminal to have the agent start filling out forms:

make run