Taprun source ↗
Entry · github

github/trending

GitHub repos created in the last N days with ≥ min_stars, filtered to AI/SaaS/devtool niches via topic+description keyword match. Supply-side signal for solo builder category emergence.

read-only

Run it

$ tap github/trending

What it returns

ColumnType
slugtext
descriptiontext
starstext
languagetext
topicstext
created_attext
urltext

Arguments

NameTypeDefaultDescription
daysint7Lookback window in days
min_starsint5Minimum stars to include
per_pageint50Max results from API

What it does

GitHub repos created in the last N days with ≥ min_stars, filtered to AI/SaaS/devtool niches via topic+description keyword match. Supply-side signal for solo builder category emergence.

Install Taprun once

Taprun ships as a single MCP server exposing a catalog of compiled taps. One-time setup on macOS / Linux:

brew install LeonTing1010/tap/taprun
tap mcp connect

Or drop this into your claude_desktop_config.json (works identically in Claude Code, Cursor, Cline, Windsurf — any MCP host):

{
  "mcpServers": {
    "tap": {
      "command": "tap",
      "args": ["mcp", "start"]
    }
  }
}

Call github/trending

Terminal, once installed:

tap run github/trending

From the MCP host — exact same compiled plan, deterministic replay, zero LLM tokens:

tap.run({ site: "github", name: "trending" })

Why compile it once

This plan was forged once — the AI read github, picked stable structural addresses (JSON-LD, ARIA, RSS, or declared API endpoints, in that priority order), and saved them to a .plan.json. Every replay since then has used zero LLM tokens. When github ships a site change that breaks the extraction, tap verify surfaces it before your data goes stale — not after your pipeline silently writes garbage for a week.

Related github taps

tapdescription
github/create-issueCreate a GitHub issue via API

Provenance

Source
LeonTing1010/tap-skills/blob/main/showcase/github/trending.plan.json
Machine format
trending.jsonld — W3C Annotation
Last verify run
never
License
MIT