AgentLaboratory

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

Fork A fork of SamuelSchmidgall/AgentLaboratory; the README may describe the upstream project.

Overview

To select a specific llm set the flag --llm-backend="llm_model" for example --llm-backend="gpt-4o" or --llm-backend="deepseek-chat". Please feel free to add a PR supporting new models according to your need!

python ai_lab_repo.py --api-key "API_KEY_HERE" --llm-backend "o1-mini" --research-topic "YOUR RESEARCH IDEA"

or, if you don't have pdflatex installed

python ai_lab_repo.py --api-key "API_KEY_HERE" --llm-backend "o1-mini" --research-topic "YOUR RESEARCH IDEA" --compile-latex "false"

To run Agent Laboratory in copilot mode, simply set the copilot-mode flag to "true"

python ai_lab_repo.py --api-key "API_KEY_HERE" --llm-backend "o1-mini" --research-topic "YOUR RESEARCH IDEA" --copilot-mode "true"

In order to add notes, you must modify the task_notes_LLM structure inside of ai_lab_repo.py. Provided below is an example set of notes used for some of our experiments.

From the project’s README on GitHub.

At a glance

Repository	Kentucky-Open-Science/AgentLaboratory
Research area	Forks of other projects
Primary language	Python
License	MIT
Stars / forks	0 / 0
Open issues and pull requests	1
Created	2025-01-16
Last push	2025-09-15
Default branch	`main`
Forked from	SamuelSchmidgall/AgentLaboratory — Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

What the README covers

Top contributors

@SamuelSchmidgall (10 commits)
@armstrongsam25 (9 commits)
@NinoRisteski (2 commits)
@CharlesCNorton (1 commit)
@krsnaa (1 commit)
@Kseymur (1 commit)
@Plavit (1 commit)
@codybum (1 commit)
@onezibo (1 commit)

Get the code

git clone https://github.com/Kentucky-Open-Science/AgentLaboratory.git