GitNova

GitHub seismograph — discoveries and growing interest

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

Three discoveries with different uses, selected from the projects GitNova tracks. This edition was saved on November 16, 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.

Tencent/LoopForge

AI agents · Go

+685stars on 2026-11-16 · UTC

Self-hosted workspace for delivering software with coding agents: a Main Bot opens Docker sandboxes, delegates to project roles, and runs SOPs (agent, script and human-gate nodes) to produce PRs with review built in.

Useful for
  • Run a built-in backend or bug-fix SOP to deliver a requirement with approval gates
  • Chat with Main Bot to explore a repo and get a PR opened automatically
  • Pause, retry or rerun a failed SOP node from its logs and artifacts
Before using
  • No license is listed in the GitHub data; check the usage terms
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2026-07-28 UTC
First seen by GitNova
2026-11-11 UTC
Typical day
+2 stars · median of 28 complete days
Magnitude
8.4 / 10 · growing interest

Already 342.5× a typical complete day; a spike in interest, not a quality score

Maximum over those 28 complete days: +904 on 2026-11-15; the current measurement has not exceeded it (UTC)

Measured: November 16, 2026, 12:40 UTC

Measurement details
  • Created on GitHub: 2026-07-28; first seen by GitNova: 2026-11-11 (UTC)
  • +685 stars measured 2026-11-16, 00:28–12:27 UTC
  • Usually: +2 stars/day — median of 28 complete days 2026-10-19–2026-11-15 (UTC)
  • Already 342.5× a typical complete day; a spike in interest, not a quality score
  • Maximum over those 28 complete days: +904 on 2026-11-15; the current measurement has not exceeded it (UTC)
  • Magnitude 8.4/10

dream-num/univer

Developer tools · TypeScript

+1,844stars on 2026-11-16 · UTC

Open-source TypeScript SDK for embedding spreadsheet, document, and presentation editors into your own product, with a plugin architecture, Canvas rendering, a formula engine, and one Facade API for browser and Node.js. Suited for SaaS, internal tools, and AI agents working with office files.

Useful for
  • Embed XLSX spreadsheet editing into a SaaS product using Univer plugins
  • Process workbooks and documents headless on Node.js in a server pipeline
  • Let an AI agent programmatically read and modify office files via the Facade API
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
2022-09-29 UTC
First seen by GitNova
2026-09-22 UTC
Typical day
+18.5 stars · median of 28 complete days
Magnitude
7.4 / 10 · growing interest

Already 99.7× a typical complete day; a spike in interest, not a quality score

The current gain already exceeds the maximum of the previous 28 complete days: +1,549 on 2026-11-15 (UTC)

Measured: November 16, 2026, 12:40 UTC

Measurement details
  • Created on GitHub: 2022-09-29; first seen by GitNova: 2026-09-22 (UTC)
  • +1,844 stars measured 2026-11-16, 00:28–12:28 UTC
  • Usually: +18.5 stars/day — median of 28 complete days 2026-10-19–2026-11-15 (UTC)
  • Already 99.7× a typical complete day; a spike in interest, not a quality score
  • The current gain already exceeds the maximum of the previous 28 complete days: +1,549 on 2026-11-15 (UTC)
  • Magnitude 7.4/10

ggml-org/ggml

Language models · C++

+161stars on 2026-11-16 · UTC

A dependency-free C/C++ tensor library for machine learning with quantization and support for CPU, GPU, NPU, and WebAssembly. It serves as a foundation for running ML models across platforms with minimal setup.

Useful for
  • Build the library from source with CMake for use in a C++ project
  • Run the examples/simple example to learn matrix multiplication
  • Apply 2-8-bit quantization to reduce tensor memory footprint
Before using
  • License: MIT
  • Installation and requirements have not been verified; review the README before running
Explore project

Why now

Created on GitHub
2022-09-18 UTC
First seen by GitNova
2026-11-14 UTC
Typical day
+5 stars · median of 28 complete days
Magnitude
7.2 / 10 · growing interest

Already 32.2× a typical complete day; a spike in interest, not a quality score

Maximum over those 28 complete days: +219 on 2026-11-15; the current measurement has not exceeded it (UTC)

Measured: November 16, 2026, 12:40 UTC

Measurement details
  • Created on GitHub: 2022-09-18; first seen by GitNova: 2026-11-14 (UTC)
  • +161 stars measured 2026-11-16, 00:28–12:28 UTC
  • Usually: +5 stars/day — median of 28 complete days 2026-10-19–2026-11-15 (UTC)
  • Already 32.2× a typical complete day; a spike in interest, not a quality score
  • Maximum over those 28 complete days: +219 on 2026-11-15; the current measurement has not exceeded it (UTC)
  • 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.