# GitHub Trending — Monday 2 November 2026

*A daily reading of GitHub’s trending page — a supplement to The AI Gazette*

- Digest: 2026-11-02
- Issued: 2 Nov 2026, 08:03 CET (Paris)
- Source: [GitHub Trending, daily](<https://github.com/trending?since=daily>), checked 2 Nov 2026, 08:00 CET; 17 repositories listed; 6 picked.

GitHub listed seventeen projects this Monday morning. The lead is **a security tool for once**: AiSOC, a self-hosted AI security operations centre that keeps a human approver in charge of responses. Claude-mem returns, not for its first place but because its new release admits that **its installer uploaded 30 days of prompts without asking**. The rest is practical: Handy for offline dictation, FreeToken for big local models, Kornia's audited 0.9.0 and Hyprland 0.57.0. Curation order reflects practical interest, not GitHub rank. Trending is not a release date or an endorsement.

> Picks are listed in curation order, not GitHub’s rank; each card shows the rank GitHub displayed when the page was checked. Stars measure attention, not security, quality or fitness for use, and no project here was installed or run. “Stars today” is GitHub’s own displayed figure for its daily window, not an audited rolling 24-hour count.

## Picks

### 1. [beenuar/AiSOC](<https://github.com/beenuar/AiSOC>)

*Security / SOC automation · GitHub rank #10 of 17 · Python · License: MIT*

**What it does:** A **self-hosted AI security operations centre**. It takes in security telemetry from pushed events or 90 data connectors (Splunk, Sentinel, Elastic, CrowdStrike, Okta, AWS and others), runs detection rules, groups alerts into incidents and has an AI agent investigate each one. Every prompt, tool call and verdict goes into an Investigation Ledger that can be exported as a signed evidence bundle, and response actions are proposed for a human to approve.

**Why it is interesting (editorial):** *First time on our list, and the only security project on today's list. Its README is unusually candid: it separates the 2,538 rules it has seen fire from the 7,023 on disk, labels synthetic demo data, and says **no hosted model provider has ever been exercised**. Response playbooks preview by default and **need three separate opt-ins plus a human approver**, a sensible default for agents near production systems.*

**Caveat:** The core profile needs Docker with about 8 GB of memory and 20 GB of disk and downloads a \~2 GB local model (Llama 3.2 3B) that is, in the README's words, not a frontier model. It is **largely one maintainer's work** (about 1,050 commits, far more than any other person) and reached v21.0.0 in six months, with a breaking change to alert grouping in that release. Its benchmark figures are the maintainer's own, and it is **not a drop-in SIEM replacement**. For authorized monitoring only; we did not run it.

**Attention, not endorsement:** GitHub showed “446 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 6,413 at the metadata check.

**Primary evidence:**

1. <https://github.com/beenuar/AiSOC>
2. <https://api.github.com/repos/beenuar/AiSOC>
3. <https://github.com/beenuar/AiSOC/releases/tag/v21.0.0>
4. <https://github.com/beenuar/AiSOC/blob/main/LICENSE>

*Metadata checked 2 Nov 2026, 08:01 CET. README read from <https://api.github.com/repos/beenuar/AiSOC/readme>, checked 2 Nov 2026, 08:01 CET.*

### 2. [thedotmack/claude-mem](<https://github.com/thedotmack/claude-mem>)

*AI agents / memory plugin · GitHub rank #1 of 17 · TypeScript · License: Apache-2.0*

**What it does:** A **persistent memory plugin for coding agents** (Claude Code, Codex, OpenCode, Gemini and others). Hooks record what the agent does in a session, a model compresses it into summaries kept in local SQLite with vector search, and later sessions get relevant context back. An optional cmem.ai cloud service adds a hosted summarizer and sync.

**Why it is interesting (editorial):** *Back on our list because of a material privacy fix, not its rank. Release v15.8.3 (2 November) states that **the browser setup opened by its installer uploaded the last 30 days of prompts** from local agent histories, with session IDs, project names, folder paths and timestamps, to cmem.ai without asking, in every version since v15.2.0. The fix makes the scan local-only until you tick which tools to upload, and adds a "Keep everything local" choice. Our 30 October card called cloud sync optional; **this behaviour was not visible in the README we read then**.*

**Caveat:** The release notes say **prompts already uploaded are not removed by this update**, and server-side handling at cmem.ai is outside the fix; the issue that reported it (5176) was still open when we checked. Anyone who ran the installer's browser setup between v15.2.0 and v15.8.2 should assume that history was sent. It still **captures everything your agent does**, so secrets in tool output can reach its database. We did not install or run it.

**Attention, not endorsement:** GitHub showed “1,526 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 109,805 at the metadata check.

**Primary evidence:**

1. <https://github.com/thedotmack/claude-mem>
2. <https://api.github.com/repos/thedotmack/claude-mem>
3. <https://github.com/thedotmack/claude-mem/releases/tag/v15.8.3>
4. <https://github.com/thedotmack/claude-mem/issues/5176>

*Metadata checked 2 Nov 2026, 08:02 CET. README read from <https://api.github.com/repos/thedotmack/claude-mem/readme>, checked 2 Nov 2026, 08:02 CET.*

### 3. [cjpais/Handy](<https://github.com/cjpais/Handy>)

*Desktop utilities / speech-to-text · GitHub rank #7 of 17 · Rust · License: MIT*

**What it does:** A **free, offline speech-to-text app** for Windows, macOS and Linux. Hold or tap a shortcut, speak, and the transcription is pasted into whatever app has focus. Silence is filtered with Silero voice detection, and you choose the speech model: Whisper (Small to Large, with GPU acceleration where available) or the CPU-friendly Parakeet V3 with automatic language detection.

**Why it is interesting (editorial):** *First time on our list. Dictation is an accessibility tool that is usually sold as a subscription or sent to a cloud service; Handy **keeps audio on your computer** and is MIT-licensed, with signed releases you can check with minisign and a CLI for controlling a running instance. It is an established project (created February 2025, v0.9.8 on 3 October) with many outside contributors in its release notes. At rank 12, anomalyco/hex is a newer app doing the same job.*

**Caveat:** Still pre-1.0, and the README lists known issues: Bluetooth headset microphones can degrade audio on macOS, and fn/Globe-key shortcuts work only on Apple keyboards. It needs **microphone and accessibility permissions** to paste into other apps, and the app downloads its speech models, which can be large, before it can transcribe (a manual route exists for restricted networks). The Homebrew and winget packages are not maintained by the Handy developers. Transcription accuracy depends on the model you pick; we did not test it.

**Attention, not endorsement:** GitHub showed “339 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 36,828 at the metadata check.

**Primary evidence:**

1. <https://github.com/cjpais/Handy>
2. <https://api.github.com/repos/cjpais/Handy>
3. <https://github.com/cjpais/Handy/releases/tag/v0.9.8>
4. <https://github.com/cjpais/Handy/blob/main/LICENSE>

*Metadata checked 2 Nov 2026, 08:00 CET. README read from <https://api.github.com/repos/cjpais/Handy/readme>, checked 2 Nov 2026, 08:01 CET.*

### 4. [FlashML-org/FreeToken](<https://github.com/FlashML-org/FreeToken>)

*AI infrastructure / local model serving · GitHub rank #16 of 17 · Python · License: Apache-2.0*

**What it does:** An **engine for serving large Mixture-of-Experts models on consumer GPUs**. It splits work between the GPU and CPU, keeps recently used experts cached in VRAM and reuses saved context when an agent edits its history, and offers OpenAI- and Anthropic-compatible APIs so coding agents such as Codex, Claude Code and OpenCode can use a local model. A desktop app for Windows and Linux is offered from its website.

**Why it is interesting (editorial):** *First time on our list. It comes with an arXiv paper whose authors include Ion Stoica, Matei Zaharia, Song Han and Kurt Keutzer, and it targets a real pain point: **running very large open-weight MoE models on one gaming PC** instead of a server. Releases are frequent; v0.2.1 (26 October) added image input for GGUF models and more model families.*

**Caveat:** The README's "290B+ models at blistering interactive speeds" is **a maintainer claim we did not measure**. The documented install needs Linux x86\_64, an NVIDIA GPU (RTX 30 series or newer) with driver r580+ and a CUDA 13 toolkit with nvcc, since kernels are compiled on first use; AMD support is marked work in progress. Model weights are large downloads with their own licences, and the docs include a guide for repairing old checkpoints in its own weight format. We did not run it.

**Attention, not endorsement:** GitHub showed “242 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 15,592 at the metadata check.

**Primary evidence:**

1. <https://github.com/FlashML-org/FreeToken>
2. <https://api.github.com/repos/FlashML-org/FreeToken>
3. <https://github.com/FlashML-org/FreeToken/releases/tag/v0.2.1>
4. <https://github.com/FlashML-org/FreeToken/blob/main/docs/install.md>
5. <https://arxiv.org/abs/2608.16157>

*Metadata checked 2 Nov 2026, 08:01 CET. README read from <https://api.github.com/repos/FlashML-org/FreeToken/readme>, checked 2 Nov 2026, 08:01 CET.*

### 5. [kornia/kornia](<https://github.com/kornia/kornia>)

*Developer tools / computer vision · GitHub rank #9 of 17 · Python · License: Apache-2.0*

**What it does:** A **differentiable computer vision library for PyTorch**: image filtering, augmentations, geometry, feature matching (SIFT, RANSAC) that run batched on the GPU and pass gradients through, so they can sit inside a training pipeline.

**Why it is interesting (editorial):** *First time on our list. Version 0.9.0 (23 October) followed what the maintainers describe as a three-month audit for silent bugs, crashes and slow-downs, with 995 community pull requests merged and **models that never worked removed**. The README now says when not to use it (one fixed blur or resize is just as easy in plain PyTorch) and publishes benchmark set-ups, and the release adds an index for coding agents.*

**Caveat:** The speed-ups in the release notes (for example 16x faster Gaussian blur on Apple CPUs, faster than OpenCV on CUDA) are **maintainer benchmarks we did not reproduce**; the notes themselves say it is about 4x slower than OpenCV on CPU. Removing broken models such as SAM3 can break code that imported them, so **pin the version and read the changelog** before upgrading. It needs PyTorch, which is a large install.

**Attention, not endorsement:** GitHub showed “101 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 11,909 at the metadata check.

**Primary evidence:**

1. <https://github.com/kornia/kornia>
2. <https://api.github.com/repos/kornia/kornia>
3. <https://github.com/kornia/kornia/releases/tag/v0.9.0>
4. <https://github.com/kornia/kornia/blob/main/LICENSE>

*Metadata checked 2 Nov 2026, 08:01 CET. README read from <https://api.github.com/repos/kornia/kornia/readme>, checked 2 Nov 2026, 08:01 CET.*

### 6. [hyprwm/Hyprland](<https://github.com/hyprwm/Hyprland>)

*Desktop / Linux window manager · GitHub rank #17 of 17 · C++ · License: BSD-3-Clause*

**What it does:** An **independent tiling Wayland compositor for Linux** (not built on wlroots, KWin or Mutter) with animations, blur, plugins, socket IPC and dwindle, master and scrolling layouts. Its configuration reloads as soon as you save it, and recent releases move it to a Lua configuration API.

**Why it is interesting (editorial):** *First time on our list, though it has been around since 2022. Version 0.57.0 (28 October) is a large release: Lua API additions such as reload\_config() and device listing, new window rules, pointer transforms, a window wobble effect and many fixes. It is a mature, actively developed project **for people who want to script their desktop**.*

**Caveat:** Linux only, and it moves fast. The 0.57.0 notes list **removal of legacy config support**, a deprecated option, two options moved to a new category and new deprecation notices, so **check your config and plugins before upgrading**. A tiling compositor takes time to set up compared with a ready-made desktop, and BSD-3-Clause licensing covers the compositor, not every plugin. We did not install it.

**Attention, not endorsement:** GitHub showed “38 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 39,510 at the metadata check.

**Primary evidence:**

1. <https://github.com/hyprwm/Hyprland>
2. <https://api.github.com/repos/hyprwm/Hyprland>
3. <https://github.com/hyprwm/Hyprland/releases/tag/v0.57.0>
4. <https://github.com/hyprwm/Hyprland/pull/15539>

*Metadata checked 2 Nov 2026, 08:01 CET. README read from <https://api.github.com/repos/hyprwm/Hyprland/readme>, checked 2 Nov 2026, 08:01 CET.*

## The full list

Every repository GitHub listed, in GitHub's order, as displayed at 2 Nov 2026, 08:00 CET.

1. [thedotmack/claude-mem](<https://github.com/thedotmack/claude-mem>) · TypeScript · 1,526 stars today · 109,800 stars in total
   *Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More*
   **Picked today** (pick 2); first covered 30 Oct 2026 at 105,064 stars; now 109,800: +4,736 stars (+4.5%) in 3 days, about 1,579 a day.
2. [lightpanda-io/browser](<https://github.com/lightpanda-io/browser>) · Zig · 825 stars today · 40,508 stars in total
   *Lightpanda: the headless browser designed for AI and automation*
   **Covered before:** first picked 31 Oct 2026 at 38,628 stars; now 40,508: +1,880 stars (+4.9%) in 2 days, about 940 a day.
3. [shiyu-coder/Kronos](<https://github.com/shiyu-coder/Kronos>) · Python · 630 stars today · 45,594 stars in total
   *Kronos: A Foundation Model for the Language of Financial Markets*
   **Covered before:** first picked 20 Oct 2026 at 41,840 stars; now 45,594: +3,754 stars (+9.0%) in 13 days, about 289 a day.
4. [pingdotgg/t3code](<https://github.com/pingdotgg/t3code>) · TypeScript · 3,094 stars today · 38,785 stars in total
   **Covered before:** first picked 31 Oct 2026 at 33,065 stars; now 38,785: +5,720 stars (+17.3%) in 2 days, about 2,860 a day.
5. [milind-soni/OpenMausBot](<https://github.com/milind-soni/OpenMausBot>) · TypeScript · 922 stars today · 10,835 stars in total
   *Open-source Grok Bot alternative with a virtual machine that bots can use*
   **Covered before:** first picked 30 Oct 2026 at 7,703 stars; now 10,835: +3,132 stars (+40.7%) in 3 days, about 1,044 a day.
6. [public-apis/public-apis](<https://github.com/public-apis/public-apis>) · Python · 324 stars today · 494,994 stars in total
   *A collective list of free APIs*
   Not covered yet.
7. [cjpais/Handy](<https://github.com/cjpais/Handy>) · Rust · 339 stars today · 36,827 stars in total
   *A free, open source, and extensible speech-to-text application that works completely offline.*
   **Picked today** (pick 3).
8. [Donchitos/Claude-Code-Game-Studios](<https://github.com/Donchitos/Claude-Code-Game-Studios>) · Shell · 967 stars today · 32,680 stars in total
   *Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.*
   **Covered before:** first picked 30 Oct 2026 at 29,601 stars; now 32,680: +3,079 stars (+10.4%) in 3 days, about 1,026 a day.
9. [kornia/kornia](<https://github.com/kornia/kornia>) · Python · 101 stars today · 11,908 stars in total
   *Geometric Computer Vision Library for Spatial AI*
   **Picked today** (pick 5).
10. [beenuar/AiSOC](<https://github.com/beenuar/AiSOC>) · Python · 446 stars today · 6,413 stars in total
   *Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.*
   **Picked today** (pick 1).
11. [Renhuai123/ziwei-doushu](<https://github.com/Renhuai123/ziwei-doushu>) · TypeScript · 941 stars today · 13,554 stars in total
   *紫微斗数开源排盘引擎 — 基于倪海厦《天纪》体系，含完整排盘算法、四化系统、格局知识库、古籍原文数据*
   **Covered before:** first picked 24 Oct 2026 at 7,018 stars; now 13,554: +6,536 stars (+93.1%) in 9 days, about 726 a day.
12. [anomalyco/hex](<https://github.com/anomalyco/hex>) · Rust · 1,179 stars today · 3,587 stars in total
   *Local voice dictation for mac, windows and linux*
   Not covered yet.
13. [CopilotKit/OpenBot](<https://github.com/CopilotKit/OpenBot>) · TypeScript · 175 stars today · 9,697 stars in total
   *Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.*
   **Covered before:** first picked 30 Oct 2026 at 8,329 stars; now 9,697: +1,368 stars (+16.4%) in 3 days, about 456 a day.
14. [togg53192-cmd/jailbreaks](<https://github.com/togg53192-cmd/jailbreaks>) · language not shown · 726 stars today · 13,205 stars in total
   *LIST OF ALL MY JAILBREAKS*
   Not covered yet.
15. [patchy631/ai-engineering-hub](<https://github.com/patchy631/ai-engineering-hub>) · Jupyter Notebook · 1,191 stars today · 40,582 stars in total
   *In-depth tutorials on LLMs, RAGs and real-world AI agent applications.*
   Not covered yet.
16. [FlashML-org/FreeToken](<https://github.com/FlashML-org/FreeToken>) · Python · 242 stars today · 15,591 stars in total
   *FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.*
   **Picked today** (pick 4).
17. [hyprwm/Hyprland](<https://github.com/hyprwm/Hyprland>) · C++ · 38 stars today · 39,510 stars in total
   *Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.*
   **Picked today** (pick 6).

## Following our picks

Then: total stars at our first pick. Now: GitHub API star count at the check time.

| Project | First picked | Stars then | Stars now | Change | Per day | Since last check |
| --- | --- | ---: | ---: | ---: | ---: | --- |
| [morluto/rea](<https://github.com/morluto/rea>) | 15 Oct 2026 | 250,334 | 419,910 | +169,576 (+67.7%) | 9,421 | +3,657 since 1 Nov 2026 |
| [debpalash/VoiceStudio](<https://github.com/debpalash/VoiceStudio>) | 15 Oct 2026 | 67,106 | 98,241 | +31,135 (+46.4%) | 1,730 | +1,149 since 1 Nov 2026 |
| [cloudflare/security-audit-skill](<https://github.com/cloudflare/security-audit-skill>) | 21 Oct 2026 | 34,638 | 56,639 | +22,001 (+63.5%) | 1,833 | +1,046 since 1 Nov 2026 |
| [MadsLorentzen/ai-job-search](<https://github.com/MadsLorentzen/ai-job-search>) | 17 Oct 2026 | 48,789 | 68,815 | +20,026 (+41.0%) | 1,252 | +304 since 1 Nov 2026 |
| [stablyai/orca](<https://github.com/stablyai/orca>) | 18 Oct 2026 | 96,443 | 112,862 | +16,419 (+17.0%) | 1,095 | +966 since 1 Nov 2026 |
| [affaan-m/ECC](<https://github.com/affaan-m/ECC>) | 16 Oct 2026 | 280,607 | 294,973 | +14,366 (+5.1%) | 845 | +741 since 1 Nov 2026 |
| [hmjz100/LinkSwift](<https://github.com/hmjz100/LinkSwift>) | 17 Oct 2026 | 23,961 | 37,284 | +13,323 (+55.6%) | 833 | +278 since 1 Nov 2026 |
| [pbakaus/impeccable](<https://github.com/pbakaus/impeccable>) | 25 Oct 2026 | 86,664 | 99,684 | +13,020 (+15.0%) | 1,628 | +1,129 since 1 Nov 2026 |
| [xerj-org/xerj](<https://github.com/xerj-org/xerj>) | 16 Oct 2026 | 5,936 | 18,702 | +12,766 (+215.1%) | 751 | +715 since 1 Nov 2026 |
| [Nutlope/hallmark](<https://github.com/Nutlope/hallmark>) | 25 Oct 2026 | 32,498 | 45,200 | +12,702 (+39.1%) | 1,588 | +1,050 since 1 Nov 2026 |
| [DietrichGebert/ponytail](<https://github.com/DietrichGebert/ponytail>) | 21 Oct 2026 | 170,170 | 182,334 | +12,164 (+7.1%) | 1,014 | +667 since 1 Nov 2026 |
| [Graphify-Labs/graphify](<https://github.com/Graphify-Labs/graphify>) | 21 Oct 2026 | 130,551 | 140,694 | +10,143 (+7.8%) | 845 | +549 since 1 Nov 2026 |
| [obra/superpowers](<https://github.com/obra/superpowers>) | 17 Oct 2026 | 300,784 | 310,794 | +10,010 (+3.3%) | 626 | +580 since 1 Nov 2026 |
| [NationalSecurityAgency/ghidra](<https://github.com/NationalSecurityAgency/ghidra>) | 15 Oct 2026 | 87,837 | 96,908 | +9,071 (+10.3%) | 504 | +353 since 1 Nov 2026 |
| [anomalyco/opencode](<https://github.com/anomalyco/opencode>) | 18 Oct 2026 | 216,421 | 223,922 | +7,501 (+3.5%) | 500 | +256 since 1 Nov 2026 |
| [HKUDS/DeepTutor](<https://github.com/HKUDS/DeepTutor>) | 28 Oct 2026 | 46,603 | 53,906 | +7,303 (+15.7%) | 1,461 | +802 since 1 Nov 2026 |
| [Renhuai123/ziwei-doushu](<https://github.com/Renhuai123/ziwei-doushu>) (on today's list, #11) | 24 Oct 2026 | 7,018 | 13,562 | +6,544 (+93.2%) | 727 | +1,034 since 1 Nov 2026 |
| [anthropics/claude-plugins-official](<https://github.com/anthropics/claude-plugins-official>) | 16 Oct 2026 | 39,407 | 45,757 | +6,350 (+16.1%) | 374 | +152 since 1 Nov 2026 |
| [Comfy-Org/ComfyUI](<https://github.com/Comfy-Org/ComfyUI>) | 18 Oct 2026 | 138,516 | 144,542 | +6,026 (+4.4%) | 402 | +151 since 1 Nov 2026 |
| [pingdotgg/t3code](<https://github.com/pingdotgg/t3code>) (on today's list, #4) | 31 Oct 2026 | 33,065 | 38,794 | +5,729 (+17.3%) | 2,864 | +2,731 since 1 Nov 2026 |
| [HKUDS/CLI-Anything](<https://github.com/HKUDS/CLI-Anything>) | 15 Oct 2026 | 52,714 | 58,064 | +5,350 (+10.1%) | 297 | +83 since 1 Nov 2026 |
| [LibreSpark/LibreTV](<https://github.com/LibreSpark/LibreTV>) | 16 Oct 2026 | 18,264 | 23,266 | +5,002 (+27.4%) | 294 | +183 since 1 Nov 2026 |
| [JetBrains/thinkrail](<https://github.com/JetBrains/thinkrail>) | 26 Oct 2026 | 2,081 | 7,057 | +4,976 (+239.1%) | 711 | +207 since 1 Nov 2026 |
| [K-Dense-AI/scientific-agent-skills](<https://github.com/K-Dense-AI/scientific-agent-skills>) | 16 Oct 2026 | 50,751 | 55,722 | +4,971 (+9.8%) | 292 | +142 since 1 Nov 2026 |
| [ruvnet/ruflo](<https://github.com/ruvnet/ruflo>) | 17 Oct 2026 | 75,720 | 80,566 | +4,846 (+6.4%) | 303 | +121 since 1 Nov 2026 |
| [thedotmack/claude-mem](<https://github.com/thedotmack/claude-mem>) (on today's list, #1) | 30 Oct 2026 | 105,064 | 109,806 | +4,742 (+4.5%) | 1,581 | +1,623 since 1 Nov 2026 |
| [TauricResearch/TradingAgents](<https://github.com/TauricResearch/TradingAgents>) | 26 Oct 2026 | 114,951 | 119,680 | +4,729 (+4.1%) | 676 | +531 since 1 Nov 2026 |
| [makecindy/cindy](<https://github.com/makecindy/cindy>) | 25 Oct 2026 | 4,269 | 8,954 | +4,685 (+109.7%) | 586 | +103 since 1 Nov 2026 |
| [akitaonrails/ai-memory](<https://github.com/akitaonrails/ai-memory>) | 18 Oct 2026 | 10,395 | 14,874 | +4,479 (+43.1%) | 299 | +121 since 1 Nov 2026 |
| [AgriciDaniel/claude-seo](<https://github.com/AgriciDaniel/claude-seo>) | 26 Oct 2026 | 21,327 | 25,685 | +4,358 (+20.4%) | 623 | +536 since 1 Nov 2026 |
| [mksglu/context-mode](<https://github.com/mksglu/context-mode>) | 15 Oct 2026 | 29,346 | 33,195 | +3,849 (+13.1%) | 214 | +134 since 1 Nov 2026 |
| [shiyu-coder/Kronos](<https://github.com/shiyu-coder/Kronos>) (on today's list, #3) | 20 Oct 2026 | 41,840 | 45,596 | +3,756 (+9.0%) | 289 | +799 since 1 Nov 2026 |
| [Panniantong/Agent-Reach](<https://github.com/Panniantong/Agent-Reach>) | 27 Oct 2026 | 104,122 | 107,763 | +3,641 (+3.5%) | 607 | +444 since 1 Nov 2026 |
| [anthropics/knowledge-work-plugins](<https://github.com/anthropics/knowledge-work-plugins>) | 21 Oct 2026 | 30,889 | 34,405 | +3,516 (+11.4%) | 293 | +163 since 1 Nov 2026 |
| [elayadesign/ai-design-skills](<https://github.com/elayadesign/ai-design-skills>) | 28 Oct 2026 | 9,991 | 13,376 | +3,385 (+33.9%) | 677 | +214 since 1 Nov 2026 |
| [xtool-org/xtool](<https://github.com/xtool-org/xtool>) | 15 Oct 2026 | 11,141 | 14,465 | +3,324 (+29.8%) | 185 | +104 since 1 Nov 2026 |
| [milind-soni/OpenMausBot](<https://github.com/milind-soni/OpenMausBot>) (on today's list, #5) | 30 Oct 2026 | 7,703 | 10,837 | +3,134 (+40.7%) | 1,045 | +940 since 1 Nov 2026 |
| [Donchitos/Claude-Code-Game-Studios](<https://github.com/Donchitos/Claude-Code-Game-Studios>) (on today's list, #8) | 30 Oct 2026 | 29,601 | 32,685 | +3,084 (+10.4%) | 1,028 | +1,302 since 1 Nov 2026 |
| [vxcontrol/pentagi](<https://github.com/vxcontrol/pentagi>) | 15 Oct 2026 | 29,886 | 32,964 | +3,078 (+10.3%) | 171 | +79 since 1 Nov 2026 |
| [luongnv89/claude-howto](<https://github.com/luongnv89/claude-howto>) | 23 Oct 2026 | 43,466 | 46,388 | +2,922 (+6.7%) | 292 | +86 since 1 Nov 2026 |
| [nightly-labs/openbot](<https://github.com/nightly-labs/openbot>) | 27 Oct 2026 | 1,697 | 4,582 | +2,885 (+170.0%) | 481 | +168 since 1 Nov 2026 |
| [headroomlabs-ai/headroom](<https://github.com/headroomlabs-ai/headroom>) | 20 Oct 2026 | 76,370 | 78,588 | +2,218 (+2.9%) | 171 | +100 since 1 Nov 2026 |
| [pollen-robotics/microduck](<https://github.com/pollen-robotics/microduck>) | 25 Oct 2026 | 11,154 | 13,309 | +2,155 (+19.3%) | 269 | +64 since 1 Nov 2026 |
| [android/skills](<https://github.com/android/skills>) | 17 Oct 2026 | 8,149 | 10,259 | +2,110 (+25.9%) | 132 | +76 since 1 Nov 2026 |
| [NVIDIA/OpenShell](<https://github.com/NVIDIA/OpenShell>) | 24 Oct 2026 | 18,934 | 20,930 | +1,996 (+10.5%) | 222 | +73 since 1 Nov 2026 |
| [gitroomhq/postiz-app](<https://github.com/gitroomhq/postiz-app>) | 27 Oct 2026 | 38,679 | 40,628 | +1,949 (+5.0%) | 325 | +199 since 1 Nov 2026 |
| [lightpanda-io/browser](<https://github.com/lightpanda-io/browser>) (on today's list, #2) | 31 Oct 2026 | 38,628 | 40,513 | +1,885 (+4.9%) | 942 | +1,096 since 1 Nov 2026 |
| [mattpocock/skills](<https://github.com/mattpocock/skills>) | 31 Oct 2026 | 307,678 | 309,454 | +1,776 (+0.6%) | 888 | +810 since 1 Nov 2026 |
| [SnailSploit/Claude-Red](<https://github.com/SnailSploit/Claude-Red>) | 24 Oct 2026 | 8,623 | 10,216 | +1,593 (+18.5%) | 177 | +96 since 1 Nov 2026 |
| [vllm-project/vllm](<https://github.com/vllm-project/vllm>) | 21 Oct 2026 | 94,532 | 96,106 | +1,574 (+1.7%) | 131 | +88 since 1 Nov 2026 |
| [anthropics/claude-code](<https://github.com/anthropics/claude-code>) | 20 Oct 2026 | 152,763 | 154,205 | +1,442 (+0.9%) | 111 | +101 since 1 Nov 2026 |
| [NVIDIA/SkillSpector](<https://github.com/NVIDIA/SkillSpector>) | 27 Oct 2026 | 22,463 | 23,897 | +1,434 (+6.4%) | 239 | +165 since 1 Nov 2026 |
| [CopilotKit/OpenBot](<https://github.com/CopilotKit/OpenBot>) (on today's list, #13) | 30 Oct 2026 | 8,329 | 9,698 | +1,369 (+16.4%) | 456 | +528 since 1 Nov 2026 |
| [supabase/supabase](<https://github.com/supabase/supabase>) | 22 Oct 2026 | 113,145 | 114,420 | +1,275 (+1.1%) | 116 | +31 since 1 Nov 2026 |
| [withmarbleapp/os-taxonomy](<https://github.com/withmarbleapp/os-taxonomy>) | 20 Oct 2026 | 6,282 | 7,501 | +1,219 (+19.4%) | 94 | +13 since 1 Nov 2026 |
| [alchaincyf/huashu-design](<https://github.com/alchaincyf/huashu-design>) | 27 Oct 2026 | 27,286 | 28,434 | +1,148 (+4.2%) | 191 | +97 since 1 Nov 2026 |
| [anthropics/skills](<https://github.com/anthropics/skills>) | 31 Oct 2026 | 185,520 | 186,471 | +951 (+0.5%) | 476 | +461 since 1 Nov 2026 |
| [twentyhq/twenty](<https://github.com/twentyhq/twenty>) | 22 Oct 2026 | 59,348 | 60,280 | +932 (+1.6%) | 85 | +55 since 1 Nov 2026 |
| [mlabonne/llm-course](<https://github.com/mlabonne/llm-course>) | 18 Oct 2026 | 83,959 | 84,853 | +894 (+1.1%) | 60 | +24 since 1 Nov 2026 |
| [coollabsio/coolify](<https://github.com/coollabsio/coolify>) | 26 Oct 2026 | 64,675 | 65,516 | +841 (+1.3%) | 120 | +82 since 1 Nov 2026 |
| [Orkas-AI/Orkas](<https://github.com/Orkas-AI/Orkas>) | 1 Nov 2026 | 6,880 | 7,678 | +798 (+11.6%) | 798 | - |
| [ruvnet/RuView](<https://github.com/ruvnet/RuView>) | 29 Oct 2026 | 101,281 | 102,043 | +762 (+0.8%) | 190 | +144 since 1 Nov 2026 |
| [Meloong-Git/PCL](<https://github.com/Meloong-Git/PCL>) | 23 Oct 2026 | 8,777 | 9,533 | +756 (+8.6%) | 76 | +24 since 1 Nov 2026 |
| [fastapi/fastapi](<https://github.com/fastapi/fastapi>) | 23 Oct 2026 | 103,901 | 104,544 | +643 (+0.6%) | 64 | +25 since 1 Nov 2026 |
| [OpenBMB/VoxCPM](<https://github.com/OpenBMB/VoxCPM>) | 24 Oct 2026 | 40,362 | 40,960 | +598 (+1.5%) | 66 | +33 since 1 Nov 2026 |
| [macro-inc/macro](<https://github.com/macro-inc/macro>) | 29 Oct 2026 | 5,555 | 6,066 | +511 (+9.2%) | 128 | +29 since 1 Nov 2026 |
| [php/php-src](<https://github.com/php/php-src>) | 23 Oct 2026 | 41,292 | 41,753 | +461 (+1.1%) | 46 | +8 since 1 Nov 2026 |
| [google-gemini/gemini-cli](<https://github.com/google-gemini/gemini-cli>) | 25 Oct 2026 | 108,241 | 108,661 | +420 (+0.4%) | 52 | +18 since 1 Nov 2026 |
| [vorssaint/vorssaint-utils](<https://github.com/vorssaint/vorssaint-utils>) | 1 Nov 2026 | 32,056 | 32,405 | +349 (+1.1%) | 349 | - |
| [expo/skills](<https://github.com/expo/skills>) | 29 Oct 2026 | 3,677 | 4,014 | +337 (+9.2%) | 84 | +26 since 1 Nov 2026 |
| [xiaolai/the-craft-of-selfteaching](<https://github.com/xiaolai/the-craft-of-selfteaching>) | 29 Oct 2026 | 18,702 | 18,998 | +296 (+1.6%) | 74 | +75 since 1 Nov 2026 |
| [lightseekorg/tokenspeed](<https://github.com/lightseekorg/tokenspeed>) | 16 Oct 2026 | 2,560 | 2,845 | +285 (+11.1%) | 17 | +10 since 1 Nov 2026 |
| [nodejs/node](<https://github.com/nodejs/node>) | 24 Oct 2026 | 122,952 | 123,192 | +240 (+0.2%) | 27 | +16 since 1 Nov 2026 |
| [bregman-arie/devops-exercises](<https://github.com/bregman-arie/devops-exercises>) | 1 Nov 2026 | 86,135 | 86,362 | +227 (+0.3%) | 227 | - |
| [aws/agent-toolkit-for-aws](<https://github.com/aws/agent-toolkit-for-aws>) | 25 Oct 2026 | 3,209 | 3,370 | +161 (+5.0%) | 20 | +6 since 1 Nov 2026 |
| [THU-MAIC/OpenMAIC](<https://github.com/THU-MAIC/OpenMAIC>) | 1 Nov 2026 | 42,284 | 42,435 | +151 (+0.4%) | 151 | - |

## Coverage notes

- All 17 listing entries were inspected. Exact primary public GitHub repository metadata was checked for the nine entries not featured before and for every pick between 07:00 and 07:03 UTC, with README files, releases and licences for the picks; all were active and unarchived, and every pick has an API-detected licence.
- thedotmack/claude-mem is a repeat (first featured 30 October). It returns only because of release v15.8.3 (2 November), a privacy fix described in its own release notes and issue 5176; its card says what changed.
- Seven entries featured before were left out without a material change: lightpanda-io/browser and pingdotgg/t3code (31 October), milind-soni/OpenMausBot, Donchitos/Claude-Code-Game-Studios and CopilotKit/OpenBot (30 October), Renhuai123/ziwei-doushu (24 October) and shiyu-coder/Kronos (20 October). Their release lists show only nightly or patch builds since their cards, or releases that predate them.
- Not picked: togg53192-cmd/jailbreaks, a list of prompts for bypassing AI model safeguards with no licence; public-apis/public-apis, a mature directory of free APIs; patchy631/ai-engineering-hub, a collection of AI tutorials that promotes its authors' newsletter; and anomalyco/hex, a newer local dictation app with a short README that overlaps Handy.
- The preceding seven calendar dates, 26 October-1 November, were checked for local history; all seven editions exist.
- The official listing was captured at 08:00:34 Europe/Paris. Literal stars-today labels are GitHub's displayed period figures; API total stars and README evidence were checked separately at the times shown per card. They are not an independently audited rolling 24-hour growth measurement.
- Feature, performance and privacy descriptions are the maintainers' own, including AiSOC's rule counts and benchmarks, FreeToken's speed claims and Kornia's release benchmarks. No candidate code, installer, plugin or model was installed, downloaded or run, and none of this is a security audit or endorsement.