GitNova

GitHub seismograph — discoveries and growing interest

GitNova Daily discoveries — November 4, 2026 · 16:00 MSK

Three discoveries with different uses, selected from the projects GitNova tracks. This edition was saved on November 4, 2026, 13:00 UTC.

Summaries come from README digests. Magnitude measures growing interest; installation has not been tested. Star counts below refer to the stated UTC day at the time shown.

Usagi-org/ai-goofish-monitor

AI agents · Python

+722stars on 2026-11-04 · UTC

A monitoring system for listings on the Chinese marketplace Xianyu (闲鱼) built on Playwright and AI: it tracks new items by given criteria, analyzes them with a multimodal model, and sends notifications. Tasks, accounts, and results are managed via a web UI.

Useful for
  • Set up a task with keywords and price range to get notifications about new listings via Telegram or Bark.
  • Run AI analysis so the model filters suitable items based on a natural-language description.
  • Deploy the system with Docker and configure account and proxy rotation to bypass platform limits.
Before using
  • License: MIT
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2025-07-16 UTC
First seen by GitNova
2026-11-03 UTC
Typical day
+30 stars · median of 28 complete days
Magnitude
8.0 / 10 · growing interest

Already 24.1× a typical complete day; a spike in interest, not a quality score

Maximum over those 28 complete days: +844 on 2026-11-03; the current measurement has not exceeded it (UTC)

Measured: November 4, 2026, 12:30 UTC

Measurement details
  • Created on GitHub: 2025-07-16; first seen by GitNova: 2026-11-03 (UTC)
  • +722 stars measured 2026-11-04, 00:17–12:12 UTC
  • Usually: +30 stars/day — median of 28 complete days 2026-10-07–2026-11-03 (UTC)
  • Already 24.1× a typical complete day; a spike in interest, not a quality score
  • Maximum over those 28 complete days: +844 on 2026-11-03; the current measurement has not exceeded it (UTC)
  • Magnitude 8.0/10

anthropics/FlashProve

Security · Lean

+311stars on 2026-11-04 · UTC

A Lean 4 research prototype for zero-knowledge proofs of AI inference: a provider proves which model produced a reply without revealing its weights. Not maintained.

Useful for
  • Verify a stored example proof with cp_verify on an ordinary CPU
  • Build and run toy proofs on CPU via blocks/first_look.sh
  • Run CPU tests with run_suite.py to check verifier correctness
Before using
  • License: Apache-2.0
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2026-10-30 UTC
First seen by GitNova
2026-11-03 UTC
Magnitude
7.5 / 10 · growing interest

Only 4 complete days of history; a reliable usual pace is not established. On 2026-11-03: +561 stars (UTC)

Maximum over those 4 complete days: +561 on 2026-11-03; the current measurement has not exceeded it (UTC)

Measured: November 4, 2026, 12:30 UTC

Measurement details
  • Created on GitHub: 2026-10-30; first seen by GitNova: 2026-11-03 (UTC)
  • +311 stars measured 2026-11-04, 00:17–12:12 UTC
  • Only 4 complete days of history; a reliable usual pace is not established. On 2026-11-03: +561 stars (UTC)
  • Maximum over those 4 complete days: +561 on 2026-11-03; the current measurement has not exceeded it (UTC)
  • Magnitude 7.5/10

Minireel/HGhub

Apps · TypeScript

+243stars on 2026-11-04 · UTC

Third-party client for the Huangguo short-drama site, built with Tauri 2, Rust and React for Windows and Android with a vertical feed and a full player (HLS + AES-128, speed, PiP).

Useful for
  • Watch short-drama episodes in a vertical feed with auto-next episode on Windows
  • Handle HLS streams with AES-128 keys through a local proxy to bypass CORS in a WebView
  • Decrypt AES-128-CBC cover images and serve them via a custom protocol
Before using
  • License: MIT
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2026-11-03 UTC
First seen by GitNova
2026-11-04 UTC
Magnitude
7.2 / 10 · growing interest

Not enough consecutive complete history days to compare daily gains

Measured: November 4, 2026, 12:30 UTC

Measurement details
  • Created on GitHub: 2026-11-03; first seen by GitNova: 2026-11-04 (UTC)
  • +243 stars measured 2026-11-04, 07:31–12:12 UTC
  • Not enough consecutive complete history days to compare daily gains
  • Magnitude 7.2/10

Share this edition

Share on XTelegram

Previous editions

Three GitHub discoveries in each edition

What they do, why they are gaining interest, and what to check before using them.

Editions at 10:00, 16:00, 22:00 MSK.