# 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

Repository: https://github.com/SamuelSchmidgall/AgentLaboratory
Canonical: https://ross.abutalabs.com/products/agentlaboratory
Language: Python
License: MIT
License Family: permissive
Last push: 2025-08-20T21:46:43+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 37, release rhythm 35, longevity 43
- inputs: {"age_days": 603, "days_push": 378, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5809, forks 804 (observed 2026-08-28T04:09:29.878525+00:00)

## What it is
Agent Laboratory is an end-to-end autonomous research workflow framework that uses specialized LLM-driven agents to assist human researchers. It automates literature reviews, experiment planning and execution, and report writing, and includes AgentRxiv for agents to share and build on research.

## Use cases
- automate literature reviews with llm agents
- run autonomous research experiments from an idea
- generate research reports and papers automatically
- let ai agents collaborate on research via agentrxiv
- speed up coding and documentation for research projects
- orchestrate multi-agent workflows for scientific discovery

## When to choose
- you want an end-to-end autonomous pipeline from literature review to written report
- you want to offload repetitive research tasks like coding experiments and documentation
- you want agents to share and build on each other's research outputs
- you prefer a human-in-the-loop system where you guide ideation

## When to avoid
- you need fully verified, publication-ready results without human review
- you lack access to LLM APIs or compute resources
- you need a lightweight single-agent assistant rather than a multi-phase workflow
- your research requires domain-specific tooling the agents don't support

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, machine-learning, workflow-automation, llm-training
- domain: artificial-intelligence, large-language-models
- platform: python, cli, cross-platform
- tags: llm-agents, autonomous-research, research-assistant, agentrxiv, scientific-discovery, multi-agent, ai-agents, research, automation

## Member repositories
- SamuelSchmidgall/AgentLaboratory (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:29.878525+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:37.595818+00:00, confidence not recorded.
  - readme: https://github.com/SamuelSchmidgall/AgentLaboratory (fetched 2026-08-28T04:09:29.878525+00:00, sha 85e418bab99d)
- Data as of 2026-08-30T08:39:29.467469+00:00.