going-doer/Paper2Code

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4982 stars · 690 forks observed · 2026-10-15

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

PaperCoder is a multi-agent LLM system that automatically generates a code repository from a machine learning research paper via a planning, analysis, and code generation pipeline. It also ships the Paper2Code benchmark datasets and model-based evaluation tooling for assessing generated repositories.

Use cases

• generate a reference implementation from an arxiv paper
• reproduce a machine learning paper as code automatically
• convert a paper pdf or latex source into a runnable repo
• benchmark llm agents on paper-to-code generation
• evaluate generated repositories with model-based judges

When to choose

• you want a starting-point implementation of an ML paper without writing it from scratch
• you need a benchmark for evaluating paper-to-code agents
• you want to run the pipeline with OpenAI models or self-hosted open-source models via vLLM

When to avoid

• you need production-ready, fully correct code rather than a faithful scaffold
• you cannot share paper content with an external LLM API and cannot host your own model
• your paper is outside machine learning

Facets

framework · maturity active

agent-framework llm-inference machine-learning rag artificial-intelligence large-language-models machine-learning developer-tools python cli cross-platform paper2code multi-agent llm code-repository-generation benchmark papercoder iclr code-generation ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="going-doer/Paper2Code")