ai-agent

JARVIS

Name: JARVIS
Author: microsoft

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

25,133 stars2,198 forksPythonUpdated 7/29/2025100% free · open source

What it does

JARVIS connects large language models (LLMs) with the machine learning community, enabling the development of AI applications through a unified interface

Install / run

git clone https://github.com/microsoft/JARVIS.git

When to use it

•You need to integrate multiple LLMs into your application
•Your project requires collaboration between data scientists and language model experts
•You want to leverage pre-trained LLMs for tasks like text classification, sentiment analysis, or language translation

Quick start

1Navigate to the cloned repository: cd JARVIS
2Create a new conda environment: conda create --name jarvis python=3.8
3Activate the environment: conda activate jarvis
4Install required packages: pip install -r requirements.txt
5Start the JARVIS server: python app.py

Ready-to-paste prompt

python app.py --model-name t5-base --task text-classification --input-text 'This is a sample text'

Heads up: Ensure you have the correct Python version (3.8) and the required packages installed, as specified in the requirements.txt file, to avoid compatibility issues

Saves to your device

Topics

deep-learning

platform

pytorch

How JARVIS works

Codeflow

Free to inspect

JARVIS is a medium Python project (~8.3k lines across 39 code files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit 13 months ago, MIT license, no tests found.

Size

Medium codebase

~8.3k lines · 39 code files · ~1 h to skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

Python

No API keys detected