Skip to content

AI Developer Tool · Python

github-discovery

MCP-native agentic discovery engine that finds high-quality GitHub repositories independent of popularity. Tiered scoring pipeline: discovery → screening → deep LLM assessment → anti-star bias ranking.

What it is

GitHub Discovery is an MCP-native agentic tool that identifies high-quality GitHub repositories through a 4-gate pipeline evaluating technical qualities independent of popularity. It provides CLI, API, and MCP server interfaces for developers and AI systems to discover repositories based on code quality, architecture, testing, and innovation.

Scored at402448118 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
AI Agents: 35.0%NLP & LLMs: 30.0%Machine Learning: 15.0%Data Science: 10.0%MLOps: 10.0%
  • AI Agents35%
  • NLP & LLMs30%
  • Machine Learning15%
  • Data Science10%
  • MLOps10%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths4

  • Comprehensive 4-gate pipeline for star-neutral GitHub repository discovery.
  • Strong engineering practices: extensive test suite (174 tests), CI, Docker support, and modular design.
  • MCP-native design enables integration with agentic AI systems (Claude Code, Kilocode, etc.).
  • Clear documentation and multiple access points (CLI, API, MCP).

Limitations

The owner keeps this project's limitations private.

Around it on the AI Agents board

Whole board
  1. 17, shared rankGnomeAI-RSAgent System · Rust68.1/100Advancedadrgu372
  2. 17, shared ranksm3Agent System · Python68.1/100AdvancedJarad Peckenpaugh
  3. 19github-discoveryAI Developer Tool · Python67.6/100AdvancedFulvio
  4. 20inlay-mwareAI Developer Tool · TypeScript67.4/100AdvancedPranav
  5. 21agent-wikiAI Developer Tool · Python67.3/100AdvancedTacoTakumi

More from Fulvio