github-deep-research

Comprehensive GitHub repository analysis through multi-round research combining API data, web search, and structured reporting. Multi-round research combining GitHub API, web_search, web_fetch to produce comprehensive markdown reports. Broad to Narrow : Start with GitHub API, then general queries, refine based on findings. Source Prioritization : Round 1 - GitHub API Directly execute scripts/github_api.py without read_file() : Available commands (the last argument of github_api.py ): Round 2 - Discovery (3-5 web_search) Round 3 - Deep Investigation (5-10 web_search + web_fetch) Round 4 - Deep Dive Follow template in assets/report_template.md : Include diagrams where helpful: Timeline (Gantt) : Architecture (Flowchart) : Comparison (Pie/Bar) : Assign confidence based on source quality: Save report as: research_{topic}_{YYYYMMDD}.md Good - With inline citations: Bad - Without citations: - Executes four research rounds: GitHub API extraction, discovery searches, deep investigation with web fetching, and timeline analysis from commits and issues - Produces structured markdown reports with executive summaries, chronological timelines, metrics tables, and Mermaid diagrams for architecture and comparisons - Implements source prioritization (official docs first, then technical blogs, news, community discussions) with confidence scoring for each claim - Includes built-in citation...