Agent Laboratory
LLM agent workflow that assists a human researcher through literature review, experiments and report writing.
Agent by Samuel Schmidgall
IndexedMIT★ 5,910
Get started
Setup steps are in the repository. Website · Repository
About
Agent Laboratory is a set of LLM-driven agents that support a human researcher through three phases: literature review, experimentation and report writing. The agents use external tools such as arXiv, Hugging Face, Python and LaTeX. The site says it adapts to available compute, from a laptop to a GPU cluster, and the human stays in charge of the research direction.
Use cases: research, coding, deep-research, writing-editing, code-generation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- research, codingagentlaboratory.github.io
- Autonomy
- Supervised: runs multi-step tasks, asks at checkpointsagentlaboratory.github.io
- Where you use it
- TerminalREADME
- Hosting
- You run itREADME
- Models
- o1, o1-preview, o1-mini, gpt-4o, o3-mini, deepseek-chatREADME
- Open source
- Yes
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Signals
- Stars
- 5,910
- Forks
- 806
- Open issues
- 40
- Last commit
- Aug 20, 2025 (1 year ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Website
- agentlaboratory.github.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Agent Laboratory. Agent Mart. https://agentmart.dev/agents/agent-laboratory (last updated 2026-10-24)