GitDealFlow Signal Agent

GitDealFlow Signal Agent

v1.0.0• GitDealFlow

Track startup engineering acceleration from public GitHub data. Returns trending startups, sector signals, and per-company velocity profiles across 20 sectors. Updated weekly. Free, no auth required.

Launch agent website ↗

Skills

• Get Trending Startups

  Return the top 20 startups ranked by engineering acceleration across all 20 sectors for the current weekly period. Each row includes commit velocity, contributor count, signal classification, and GitHub URL.

  startupstrendingvcdeal-flowgithubweekly

• Search Startups by Sector

  Return every tracked startup within a sector, ranked by engineering acceleration for the current weekly period. Common slugs: ai-ml, cybersecurity, developer-tools, healthcare, climate-tech, enterprise-saas, data-infrastructure, web3, robotics, edtech, ecommerce-infrastructure, supply-chain, legal-tech, hr-tech, proptech, agtech, gaming, space-tech, social-community. The active list rotates weekly — call get_signals_summary first for the canonical set, or pass an unknown slug to receive `availableSectors` in the error payload.

  startupssectorfiltervcdeal-flow

• Get Startup Signal Profile

  Return the full engineering-acceleration profile for a single tracked startup: commit velocity, velocity change, contributor count and growth, new-repo count, signal classification, sector, stage, geography, and GitHub URL. Matching is case-insensitive and accepts display name or GitHub org slug.

  startuplookupprofiledue-diligence

• Get Dataset Summary

  Return a high-level snapshot of the dataset: current reporting period, active sectors, total startups tracked, last-refresh timestamp, update frequency, citation string, and direct URLs to every data format (JSON, CSV, RSS, OpenAPI, llms.txt).

  metafreshnesscitationformats

• Get Signal Methodology

  Return the methodology behind the signal: how startup engineering activity is sourced from public GitHub, how commit velocity and contributor-growth metrics are computed, how signal types ('breakout' | 'acceleration' | 'steady' | 'cooling') are classified, refresh cadence, and known limitations.

  methodologytrustinterpretabilitycitation

Integration

import asyncio
from a2a_registry import AsyncRegistry

async def main():
    async with AsyncRegistry() as registry:
        agent = await registry.get_by_id("4eb0310e-5c8b-4e07-9fbd-6f7d86db553b")
        client = await agent.async_connect()
        print(f"Connected to {agent.name}")

asyncio.run(main())