# jmiao24/Paper2Agent

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

Repository: https://github.com/jmiao24/Paper2Agent
Canonical: https://ross.abutalabs.com/products/paper2agent
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-02-10T22:03:46+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 66, release rhythm 35, longevity 25
- inputs: {"age_days": 358, "days_push": 204, "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 2338, forks 347 (observed 2026-08-28T04:06:38.533830+00:00)

## What it is
Paper2Agent is a multi-agent AI system that automatically converts research paper codebases into interactive AI agents with minimal human input. It analyzes a GitHub repository, detects its tutorials, and generates agents that can perform the paper's analyses.

## Use cases
- turn a research paper's codebase into an interactive AI agent
- automatically run tutorials from a paper's GitHub repo
- create an agent for single-cell transcriptomics analysis from the TISSUE paper
- build a Scanpy agent for preprocessing and clustering
- reproduce analyses from papers without reading the code manually

## When to choose
- you want to make a published paper's methods usable as a conversational agent
- you need to automate running tutorials from a research codebase
- you work in computational biology and want paper-derived analysis agents

## When to avoid
- you need a fast or free pipeline - runs can take 30 minutes to 3+ hours and cost ~$15 in LLM API fees
- the paper has no public codebase or tutorials to analyze
- you need fully deterministic, non-LLM-driven reproducibility

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, developer-tools
- domain: artificial-intelligence, large-language-models, developer-tools, bioinformatics
- platform: python, cli, cross-platform
- tags: multi-agent, research-papers, paper-to-agent, claude, scientific-computing, automation, ai-agents

## Member repositories
- jmiao24/Paper2Agent (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:38.533830+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 2026-08-30T02:37:32.382774+00:00, confidence not recorded.
  - readme: https://github.com/jmiao24/Paper2Agent (fetched 2026-08-28T04:06:38.533830+00:00, sha 8db223a2c143)
- Data as of 2026-08-30T08:39:29.467469+00:00.