paperpilot 0.2.0

A CLI research agent for AI-related paper search, code discovery, PDF collection, and bilingual reports.

PaperPilot

A CLI AI literature search agent that follows a Planner + Tool Pipeline + Reflection + Report Writer architecture.

Quick Start

pip install -e .
PaperPilot

Command mode:

PaperPilot "LLM agent" --auto-confirm --max-papers 30 --since-year 2021

LLM Config

Recommended:

PaperPilot config set --base-url https://api.deepseek.com --model deepseek-chat
PaperPilot config show

The config is stored at ~/.paperpilot/config.json with file mode 600 where supported.

Priority:

1. Environment variables: OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL
2. User config: ~/.paperpilot/config.json
3. Legacy project file: llmapi.txt

Without an LLM key, the CLI still runs with deterministic fallback query planning and templated reports.

Outputs

Each run writes:

• task.json
• query_understanding.md
• plan.json
• metadata.json
• ranked_papers.json
• reflection.json
• report.zh.md
• report.en.md
• report.zh.pdf
• report.en.pdf
• download_log.json
• pdfs/

GitHub Filter

literature-agent "retrieval augmented generation" --auto-confirm --github-filter required

• any: keep all papers and annotate code availability.
• required: keep papers with a detected public code link.
• none: keep papers without detected public code links.