yangaona GitHub avatar

paper-distill-agent

yangaona

A local CLI tool for deep reading of PDF papers with traceable evidence, using the DeepSeek API to extract atomic facts, generate structured paper cards, and produce Markdown summaries and Mermaid architecture diagrams.

Stars

3

7-day growth

No data

Forks

0

Open issues

0

License

No data

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides transparent, evidence-backed paper analysis by linking each claim to specific PDF pages, and outputs both human-readable summaries and machine-readable architecture diagrams, all running locally with user-controlled API calls.

Who it is for

  • Researchers who need to quickly comprehend multiple papers
  • Students learning to critically read academic literature
  • Developers building automated paper analysis pipelines
  • Anyone seeking a reproducible, citation-aware reading assistant

Use cases

  • Batch-analyzing a collection of PDF papers from a conference or journal
  • Extracting structured facts and architecture from a complex methods section
  • Creating a shareable reading note with page-level evidence for claims
  • Iteratively refining understanding by re-running the agent with different models or prompts

Strengths

  • Local execution with optional dry-run for PDF parsing verification
  • Every factual claim traced to specific PDF page numbers via evidence_id
  • Structured output including summary Markdown and Mermaid flowchart
  • Supports batch processing of multiple PDFs into separate result directories

Considerations

  • Requires a DeepSeek API key and internet connection for the full summarization pipeline
  • PDF parsing quality depends on pypdf or pdftotext; scanned PDFs may not be supported
  • Limited to command-line interface; no graphical user interface for non-technical users

README quick start

安装

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
mshumer
Featured
mshumer GitHub avatar

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents
1,234