GitNova

GitHub seismograph — discoveries and growing interest

GitNova Daily discoveries — October 14, 2026 · 16:00 MSK

Three discoveries with different uses, selected from the projects GitNova tracks. This edition was saved on October 14, 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.

vercel-labs/skills

AI agents · TypeScript

+344stars on 2026-10-14 · UTC

CLI for the open agent skills ecosystem: installs, finds and runs reusable skills from Git repositories across Claude Code, Codex, Cursor, OpenCode and 75+ other agents.

Useful for
  • Install a set of skills from a GitHub repository into Claude Code with one npx skills add command
  • Generate a single skill's prompt without installing via skills use and pipe it into an agent
  • Add a private skills repository over SSH or GitHub CLI using existing Git authentication
Before using
  • License: MIT
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2026-01-14 UTC
First seen by GitNova
2026-09-13 UTC
Typical day
+80.5 stars · median of 28 complete days
Magnitude
7.3 / 10 · growing interest

Already 4.3× a typical complete day; a spike in interest, not a quality score

Maximum over those 28 complete days: +649 on 2026-10-13; the current measurement has not exceeded it (UTC)

Measured: October 14, 2026, 12:55 UTC

Measurement details
  • Created on GitHub: 2026-01-14; first seen by GitNova: 2026-09-13 (UTC)
  • +344 stars measured 2026-10-14, 00:37–12:35 UTC
  • Usually: +80.5 stars/day — median of 28 complete days 2026-09-16–2026-10-13 (UTC)
  • Already 4.3× a typical complete day; a spike in interest, not a quality score
  • Maximum over those 28 complete days: +649 on 2026-10-13; the current measurement has not exceeded it (UTC)
  • Magnitude 7.3/10

snuri00/ps2-web-recomp

Games & graphics · C++

+73stars on 2026-10-14 · UTC

Static recompilation of PlayStation 2 games to WebAssembly with a native runtime: Emotion Engine code is translated to C++ and the PS2 OS and hardware are reimplemented, rendering via WebGPU. Games run in the browser without an emulator, using your own disc image.

Useful for
  • Run Gran Turismo 4 or God of War II in the browser from your own disc image
  • Build a WebAssembly version of a PS2 game using the repository scripts
  • Study static recompilation of the R5900 and PS2 vector units from the open code
Before using
  • License: MIT
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2026-10-08 UTC
First seen by GitNova
2026-10-12 UTC
Magnitude
7.0 / 10 · growing interest

Only 5 complete days of history; a reliable usual pace is not established. On 2026-10-13: +299 stars (UTC)

Maximum over those 5 complete days: +445 on 2026-10-12; the current measurement has not exceeded it (UTC)

Measured: October 14, 2026, 12:55 UTC

Measurement details
  • Created on GitHub: 2026-10-08; first seen by GitNova: 2026-10-12 (UTC)
  • +73 stars measured 2026-10-14, 00:37–12:35 UTC
  • Only 5 complete days of history; a reliable usual pace is not established. On 2026-10-13: +299 stars (UTC)
  • Maximum over those 5 complete days: +445 on 2026-10-12; the current measurement has not exceeded it (UTC)
  • Magnitude 7.0/10

vxcontrol/pentagi

Security · Go

+531stars on 2026-10-14 · UTC

Autonomous multi-agent system in Go for automated penetration testing: AI agents plan and execute steps in an isolated Docker sandbox with 20+ tools (nmap, metasploit, sqlmap).

Useful for
  • Run an automated penetration test against a target system via the web UI
  • Connect your own LLM provider (OpenAI, Anthropic, Ollama) for the agents
  • Generate a vulnerability report with exploitation guides in Markdown or PDF
Before using
  • License: MIT
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2025-01-06 UTC
First seen by GitNova
2026-09-13 UTC
Typical day
+39.5 stars · median of 28 complete days
Magnitude
6.9 / 10 · growing interest

Already 13.4× a typical complete day; a spike in interest, not a quality score

Maximum over those 28 complete days: +1,924 on 2026-10-12; the current measurement has not exceeded it (UTC)

Measured: October 14, 2026, 12:55 UTC

Measurement details
  • Created on GitHub: 2025-01-06; first seen by GitNova: 2026-09-13 (UTC)
  • +531 stars measured 2026-10-14, 00:37–12:35 UTC
  • Usually: +39.5 stars/day — median of 28 complete days 2026-09-16–2026-10-13 (UTC)
  • Already 13.4× a typical complete day; a spike in interest, not a quality score
  • Maximum over those 28 complete days: +1,924 on 2026-10-12; the current measurement has not exceeded it (UTC)
  • Magnitude 6.9/10

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.

Read daily discoveries in English Project updates · English RSS Telegram · in Russian