Building RepoRank — The Open Source Impact & Funding Readiness Engine

Description and use

RepoRank aggregates metrics from GitHub, PyPI, npm, HackerNews, and Open Collective via Coral SQL, then uses an LLM to produce impact scores, narratives, pitches, and grant recommendations, streamlining funding proposal preparation.

Problem

Maintainers struggle to compile impact metrics from multiple APIs to craft grant proposals and sponsorship applications.

Outcome

RepoRank reduces data aggregation from days to seconds, produces a 0‑100 impact score, a concise pitch, and targeted grant suggestions, streamlining funding workflows for open‑source maintainers.

Workflow

• Define custom YAML source specs for PyPI, npm, HackerNews, Open Collective
• Integrate sources into Coral SQL engine
• Write a single cross-source JOIN query to fetch metrics
• Execute query via Coral to obtain unified JSON
• Pass JSON to Hugging Face Qwen 2.5 (72B) for analysis
• Generate impact score, narrative, pitch, and grant recommendations
• Display results in a dark‑mode dashboard with radar charts and grant cards

Evidence

Integrating 4+ external APIs usually takes days of reading docs and writing API wrapper code.

Source

Coral changes this completely by letting you query APIs using standard SQL.

Source

Using structured JSON schema outputs, Qwen acts as an expert open-source analyst, returning Impact Score, Narrative, Pitch, and Targeted Grants.

Source