# GitHub Trending — Saturday 31 October 2026

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

- Digest: 2026-10-31
- Issued: 31 Oct 2026, 08:03 CET (Paris)
- Source: [GitHub Trending, daily](<https://github.com/trending?since=daily>), checked 31 Oct 2026, 08:00 CET; 15 repositories listed; 4 picked.

GitHub listed fifteen projects this Saturday morning. Ten had been featured in the past week and none showed a change big enough to bring it back, so all four picks are first-time entries. Lightpanda leads as **a headless browser built from scratch for automation**, the most distinct project on a list otherwise dominated by coding agents. T3 Code puts several coding agents behind one app you can reach from a phone, and two skill collections, Matt Pocock's and Anthropic's own, show **two contrasting ways of teaching agents a workflow**. The remaining new entry, a collection of model jailbreak prompts, was left out again. 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. [lightpanda-io/browser](<https://github.com/lightpanda-io/browser>)

*Developer tools / browser automation · GitHub rank #15 of 15 · Zig · License: AGPL-3.0*

**What it does:** A **headless browser written from scratch in Zig** for scraping, testing and AI agents, not a Chromium or WebKit fork. It runs JavaScript with V8, parses HTML with html5ever and serves the Chrome DevTools Protocol and WebDriver BiDi, so existing Puppeteer or Playwright scripts can connect to it. It can also dump pages as HTML, Markdown or structured data, act as an MCP server with a separate browsing session per client, and run a built-in agent mode.

**Why it is interesting (editorial):** *First time on our list. Headless Chrome is the default for automation but heavy at scale; Lightpanda drops graphical rendering altogether, and its README claims about 16 times less memory and 9 times faster runs than headless Chrome on 100 pages (the maintainers' benchmark on one AWS instance, not ours). The agent mode has a practical twist: **prototype with a model, then save and replay a deterministic script** that needs no model or tokens at runtime.*

**Caveat:** Licensed **AGPL-3.0**, which matters if you offer it as a network service, and contributions require a CLA. **Usage telemetry is on by default** (LIGHTPANDA\_DISABLE\_TELEMETRY=true turns it off). It is not a full browser: with no rendering engine, PNG and PDF dumps are text-only, and web compatibility is tracked against Web Platform Tests rather than guaranteed. There is no native Windows or musl (Alpine) build, and the Homebrew and AUR packages track nightlies rather than the 1.0.2 release. We did not run it or its benchmark.

**Attention, not endorsement:** GitHub showed “626 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 38,628 at the metadata check.

**Primary evidence:**

1. <https://github.com/lightpanda-io/browser>
2. <https://api.github.com/repos/lightpanda-io/browser>
3. <https://github.com/lightpanda-io/browser/blob/main/LICENSE>
4. <https://github.com/lightpanda-io/browser/releases/tag/1.0.2>
5. <https://github.com/lightpanda-io/demo/blob/main/BENCHMARKS.md>

*Metadata checked 31 Oct 2026, 08:01 CET. README read from <https://api.github.com/repos/lightpanda-io/browser/readme>, checked 31 Oct 2026, 08:01 CET.*

### 2. [pingdotgg/t3code](<https://github.com/pingdotgg/t3code>)

*Developer tools / AI agents · GitHub rank #9 of 15 · TypeScript · License: MIT*

**What it does:** An **open-source control surface for the coding agents already on your machine**: Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity, through the subscriptions you already have. A local server runs the agents, and you drive them from a web app, an Electron desktop app or iOS and Android apps, connecting remotely through its T3 Connect tunnel, LAN pairing or Tailscale.

**Why it is interesting (editorial):** *First time on our list. Rather than another agent, it is one interface over several, MIT-licensed so it can be forked. The practical draw is **running agents on a desktop or server and steering them from a phone**; devices pair through one-time links, and sessions can be listed and revoked. The FAQ is unusually frank, for example noting that Claude use through Anthropic's Agent SDK drains five-hour limits faster than Claude Code itself.*

**Caveat:** The README says it is **very early: expect bugs**, and it is mostly not accepting contributions; most recent builds are nightlies and previews (latest stable v0.1.5, 29 October). Pairing a device gives it control of your machine's agents, so treat pairing links like keys. T3 Connect is free for up to three machines "for now", basic usage events (provider, model, token totals) are sent unless T3CODE\_TELEMETRY\_ENABLED=false, and the FAQ's tips on pooling several subscriptions come with its own warning that accounts could be banned. We did not install it.

**Attention, not endorsement:** GitHub showed “930 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 33,065 at the metadata check.

**Primary evidence:**

1. <https://github.com/pingdotgg/t3code>
2. <https://api.github.com/repos/pingdotgg/t3code>
3. <https://github.com/pingdotgg/t3code/blob/main/LICENSE>
4. <https://github.com/pingdotgg/t3code/releases/tag/v0.1.5>
5. <https://github.com/pingdotgg/t3code/blob/main/docs/user/faq.md>
6. <https://github.com/pingdotgg/t3code/blob/main/docs/user/remote-access.md>

*Metadata checked 31 Oct 2026, 08:01 CET. README read from <https://api.github.com/repos/pingdotgg/t3code/readme>, checked 31 Oct 2026, 08:01 CET.*

### 3. [mattpocock/skills](<https://github.com/mattpocock/skills>)

*Developer tools / agent skills · GitHub rank #8 of 15 · Shell · License: MIT*

**What it does:** Matt Pocock's **personal set of agent skills for engineering work**, packaged as plugins for Claude Code, Codex and GitHub Copilot, or as editable files for Gemini CLI, Cursor, OpenCode and others. They cover alignment (grill-me, grill-with-docs), planning (to-spec, to-tickets, wayfinder), test-driven development, bug diagnosis, code review and architecture surveys, after a one-time setup that records your issue tracker, triage labels and docs location.

**Why it is interesting (editorial):** *First time on our list, although it is one of the most-starred skill collections on GitHub. Unlike frameworks that own the whole process, these are **small, composable skills meant to be edited**, grounded in named classics such as The Pragmatic Programmer and Domain-Driven Design. Having the agent interview you before it writes code, and keeping a project glossary to cut its verbosity, are ideas worth borrowing even without installing anything.*

**Caveat:** The plugin installs **update themselves by default**, so the instructions your agent follows can change without your review; the skills.sh route copies files you update by hand. Several skills write to your issue tracker and repo docs: v1.3.2 (29 October) fixed a template that had let agents working in clones of this repo file their tickets into it. It is one practitioner's workflow, opinions included, and the README also promotes his newsletter. We did not install it.

**Attention, not endorsement:** GitHub showed “876 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 307,678 at the metadata check.

**Primary evidence:**

1. <https://github.com/mattpocock/skills>
2. <https://api.github.com/repos/mattpocock/skills>
3. <https://github.com/mattpocock/skills/blob/main/LICENSE>
4. <https://github.com/mattpocock/skills/releases/tag/v1.3.2>

*Metadata checked 31 Oct 2026, 08:01 CET. README read from <https://api.github.com/repos/mattpocock/skills/readme>, checked 31 Oct 2026, 08:01 CET.*

### 4. [anthropics/skills](<https://github.com/anthropics/skills>)

*AI agents / skills reference · GitHub rank #11 of 15 · Python · License: Mixed: Apache-2.0 and proprietary*

**What it does:** Anthropic's public repository of **Agent Skills: folders of instructions, scripts and resources** that Claude loads for specialised tasks. It holds the Agent Skills specification, a template, and examples from art and design to MCP server building, web-app testing and the Claude API, plus the docx, pdf, pptx and xlsx skills that the README says power Claude's own document features. It can be added to Claude Code as a plugin marketplace.

**Why it is interesting (editorial):** *First time on our list. It is the reference implementation of a format that several other projects on today's list also use, and **the production document skills are readable examples** of how complex skills are built. It is kept current: the mcp-builder skill was updated on 28 October to teach v2 of the MCP TypeScript SDK.*

**Caveat:** **Licensing is mixed**: many skills are Apache-2.0, but the four document skills are source-available under Anthropic's terms, and their licence file forbids keeping copies outside Anthropic's services. GitHub detects no repository-wide licence. The README says the skills are **for demonstration and educational purposes only** and that Claude's built-in behaviour may differ. Skills include scripts an agent can run, so review them like code. We did not install them.

**Attention, not endorsement:** GitHub showed “295 stars today” as displayed for GitHub's daily window (not an audited rolling 24-hour count). Total stars: 185,520 at the metadata check.

**Primary evidence:**

1. <https://github.com/anthropics/skills>
2. <https://api.github.com/repos/anthropics/skills>
3. <https://github.com/anthropics/skills/blob/main/skills/pdf/LICENSE.txt>
4. <https://github.com/anthropics/skills/blob/main/skills/mcp-builder/LICENSE.txt>
5. <https://github.com/anthropics/skills/tree/main/spec>

*Metadata checked 31 Oct 2026, 08:01 CET. README read from <https://api.github.com/repos/anthropics/skills/readme>, checked 31 Oct 2026, 08:01 CET.*

## The full list

Every repository GitHub listed, in GitHub's order, as displayed at 31 Oct 2026, 08:00 CET.

1. [thedotmack/claude-mem](<https://github.com/thedotmack/claude-mem>) · TypeScript · 1,140 stars today · 106,685 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*
   **Covered before:** first picked 30 Oct 2026 at 105,064 stars; now 106,685: +1,621 stars (+1.5%) in 1 day.
2. [milind-soni/OpenMausBot](<https://github.com/milind-soni/OpenMausBot>) · TypeScript · 895 stars today · 8,954 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 8,954: +1,251 stars (+16.2%) in 1 day.
3. [pbakaus/impeccable](<https://github.com/pbakaus/impeccable>) · Rust · 2,300 stars today · 97,396 stars in total
   *The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.*
   **Covered before:** first picked 25 Oct 2026 at 86,664 stars; now 97,396: +10,732 stars (+12.4%) in 6 days, about 1,789 a day.
4. [CopilotKit/OpenBot](<https://github.com/CopilotKit/OpenBot>) · TypeScript · 706 stars today · 8,934 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 8,934: +605 stars (+7.3%) in 1 day.
5. [Renhuai123/ziwei-doushu](<https://github.com/Renhuai123/ziwei-doushu>) · TypeScript · 1,126 stars today · 11,569 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 11,569: +4,551 stars (+64.8%) in 7 days, about 650 a day.
6. [expo/skills](<https://github.com/expo/skills>) · Shell · 38 stars today · 3,939 stars in total
   *A collection of AI agent skills for working with Expo projects and Expo Application Services*
   **Covered before:** first picked 29 Oct 2026 at 3,677 stars; now 3,939: +262 stars (+7.1%) in 2 days, about 131 a day.
7. [macro-inc/macro](<https://github.com/macro-inc/macro>) · Rust · 57 stars today · 5,946 stars in total
   *Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.*
   **Covered before:** first picked 29 Oct 2026 at 5,555 stars; now 5,946: +391 stars (+7.0%) in 2 days, about 196 a day.
8. [mattpocock/skills](<https://github.com/mattpocock/skills>) · Shell · 876 stars today · 307,678 stars in total
   *Skills for Real Engineers. Straight from my .agents directory.*
   **Picked today** (pick 3).
9. [pingdotgg/t3code](<https://github.com/pingdotgg/t3code>) · TypeScript · 930 stars today · 33,064 stars in total
   **Picked today** (pick 2).
10. [HKUDS/DeepTutor](<https://github.com/HKUDS/DeepTutor>) · Python · 2,282 stars today · 52,006 stars in total
   *DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.*
   **Covered before:** first picked 28 Oct 2026 at 46,603 stars; now 52,006: +5,403 stars (+11.6%) in 3 days, about 1,801 a day.
11. [anthropics/skills](<https://github.com/anthropics/skills>) · Python · 295 stars today · 185,519 stars in total
   *Public repository for Agent Skills*
   **Picked today** (pick 4).
12. [JetBrains/thinkrail](<https://github.com/JetBrains/thinkrail>) · TypeScript · 722 stars today · 6,675 stars in total
   *Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need*
   **Covered before:** first picked 26 Oct 2026 at 2,081 stars; now 6,675: +4,594 stars (+220.8%) in 5 days, about 919 a day.
13. [togg53192-cmd/jailbreaks](<https://github.com/togg53192-cmd/jailbreaks>) · language not shown · 2,055 stars today · 11,534 stars in total
   *LIST OF ALL MY JAILBREAKS*
   Not covered yet.
14. [obra/superpowers](<https://github.com/obra/superpowers>) · Shell · 1,259 stars today · 309,577 stars in total
   *An agentic skills framework & software development methodology that works.*
   **Covered before:** first picked 17 Oct 2026 at 300,784 stars; now 309,577: +8,793 stars (+2.9%) in 14 days, about 628 a day. Also picked 28 Oct 2026.
15. [lightpanda-io/browser](<https://github.com/lightpanda-io/browser>) · Zig · 626 stars today · 38,627 stars in total
   *Lightpanda: the headless browser designed for AI and automation*
   **Picked today** (pick 1).

## 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 | 413,128 | +162,794 (+65.0%) | 10,175 | +4,009 since 30 Oct 2026 |
| [debpalash/VoiceStudio](<https://github.com/debpalash/VoiceStudio>) | 15 Oct 2026 | 67,106 | 96,015 | +28,909 (+43.1%) | 1,807 | +1,351 since 30 Oct 2026 |
| [cloudflare/security-audit-skill](<https://github.com/cloudflare/security-audit-skill>) | 21 Oct 2026 | 34,638 | 54,415 | +19,777 (+57.1%) | 1,978 | +1,271 since 30 Oct 2026 |
| [MadsLorentzen/ai-job-search](<https://github.com/MadsLorentzen/ai-job-search>) | 17 Oct 2026 | 48,789 | 68,112 | +19,323 (+39.6%) | 1,380 | +529 since 30 Oct 2026 |
| [stablyai/orca](<https://github.com/stablyai/orca>) | 18 Oct 2026 | 96,443 | 111,288 | +14,845 (+15.4%) | 1,142 | +869 since 30 Oct 2026 |
| [affaan-m/ECC](<https://github.com/affaan-m/ECC>) | 16 Oct 2026 | 280,607 | 293,540 | +12,933 (+4.6%) | 862 | +651 since 30 Oct 2026 |
| [hmjz100/LinkSwift](<https://github.com/hmjz100/LinkSwift>) | 17 Oct 2026 | 23,961 | 36,741 | +12,780 (+53.3%) | 913 | +355 since 30 Oct 2026 |
| [xerj-org/xerj](<https://github.com/xerj-org/xerj>) | 16 Oct 2026 | 5,936 | 17,797 | +11,861 (+199.8%) | 791 | +194 since 30 Oct 2026 |
| [DietrichGebert/ponytail](<https://github.com/DietrichGebert/ponytail>) | 21 Oct 2026 | 170,170 | 181,100 | +10,930 (+6.4%) | 1,093 | +687 since 30 Oct 2026 |
| [pbakaus/impeccable](<https://github.com/pbakaus/impeccable>) (on today's list, #3) | 25 Oct 2026 | 86,664 | 97,399 | +10,735 (+12.4%) | 1,789 | +1,483 since 30 Oct 2026 |
| [Nutlope/hallmark](<https://github.com/Nutlope/hallmark>) | 25 Oct 2026 | 32,498 | 43,231 | +10,733 (+33.0%) | 1,789 | +950 since 30 Oct 2026 |
| [Graphify-Labs/graphify](<https://github.com/Graphify-Labs/graphify>) | 21 Oct 2026 | 130,551 | 139,610 | +9,059 (+6.9%) | 906 | +680 since 30 Oct 2026 |
| [obra/superpowers](<https://github.com/obra/superpowers>) (on today's list, #14) | 17 Oct 2026 | 300,784 | 309,579 | +8,795 (+2.9%) | 628 | +722 since 30 Oct 2026 |
| [NationalSecurityAgency/ghidra](<https://github.com/NationalSecurityAgency/ghidra>) | 15 Oct 2026 | 87,837 | 96,269 | +8,432 (+9.6%) | 527 | +306 since 30 Oct 2026 |
| [anomalyco/opencode](<https://github.com/anomalyco/opencode>) | 18 Oct 2026 | 216,421 | 223,394 | +6,973 (+3.2%) | 536 | +257 since 30 Oct 2026 |
| [anthropics/claude-plugins-official](<https://github.com/anthropics/claude-plugins-official>) | 16 Oct 2026 | 39,407 | 45,473 | +6,066 (+15.4%) | 404 | +128 since 30 Oct 2026 |
| [Comfy-Org/ComfyUI](<https://github.com/Comfy-Org/ComfyUI>) | 18 Oct 2026 | 138,516 | 144,242 | +5,726 (+4.1%) | 440 | +194 since 30 Oct 2026 |
| [HKUDS/DeepTutor](<https://github.com/HKUDS/DeepTutor>) (on today's list, #10) | 28 Oct 2026 | 46,603 | 52,008 | +5,405 (+11.6%) | 1,802 | +1,205 since 30 Oct 2026 |
| [HKUDS/CLI-Anything](<https://github.com/HKUDS/CLI-Anything>) | 15 Oct 2026 | 52,714 | 57,862 | +5,148 (+9.8%) | 322 | +105 since 30 Oct 2026 |
| [K-Dense-AI/scientific-agent-skills](<https://github.com/K-Dense-AI/scientific-agent-skills>) | 16 Oct 2026 | 50,751 | 55,442 | +4,691 (+9.2%) | 313 | +123 since 30 Oct 2026 |
| [LibreSpark/LibreTV](<https://github.com/LibreSpark/LibreTV>) | 16 Oct 2026 | 18,264 | 22,903 | +4,639 (+25.4%) | 309 | +156 since 30 Oct 2026 |
| [ruvnet/ruflo](<https://github.com/ruvnet/ruflo>) | 17 Oct 2026 | 75,720 | 80,336 | +4,616 (+6.1%) | 330 | +148 since 30 Oct 2026 |
| [JetBrains/thinkrail](<https://github.com/JetBrains/thinkrail>) (on today's list, #12) | 26 Oct 2026 | 2,081 | 6,675 | +4,594 (+220.8%) | 919 | +477 since 30 Oct 2026 |
| [Renhuai123/ziwei-doushu](<https://github.com/Renhuai123/ziwei-doushu>) (on today's list, #5) | 24 Oct 2026 | 7,018 | 11,572 | +4,554 (+64.9%) | 651 | +1,053 since 30 Oct 2026 |
| [makecindy/cindy](<https://github.com/makecindy/cindy>) | 25 Oct 2026 | 4,269 | 8,743 | +4,474 (+104.8%) | 746 | +115 since 30 Oct 2026 |
| [akitaonrails/ai-memory](<https://github.com/akitaonrails/ai-memory>) | 18 Oct 2026 | 10,395 | 14,630 | +4,235 (+40.7%) | 326 | +147 since 30 Oct 2026 |
| [TauricResearch/TradingAgents](<https://github.com/TauricResearch/TradingAgents>) | 26 Oct 2026 | 114,951 | 118,786 | +3,835 (+3.3%) | 767 | +348 since 30 Oct 2026 |
| [mksglu/context-mode](<https://github.com/mksglu/context-mode>) | 15 Oct 2026 | 29,346 | 32,966 | +3,620 (+12.3%) | 226 | +89 since 30 Oct 2026 |
| [AgriciDaniel/claude-seo](<https://github.com/AgriciDaniel/claude-seo>) | 26 Oct 2026 | 21,327 | 24,640 | +3,313 (+15.5%) | 663 | +510 since 30 Oct 2026 |
| [anthropics/knowledge-work-plugins](<https://github.com/anthropics/knowledge-work-plugins>) | 21 Oct 2026 | 30,889 | 34,085 | +3,196 (+10.3%) | 320 | +185 since 30 Oct 2026 |
| [xtool-org/xtool](<https://github.com/xtool-org/xtool>) | 15 Oct 2026 | 11,141 | 14,275 | +3,134 (+28.1%) | 196 | +77 since 30 Oct 2026 |
| [elayadesign/ai-design-skills](<https://github.com/elayadesign/ai-design-skills>) | 28 Oct 2026 | 9,991 | 12,935 | +2,944 (+29.5%) | 981 | +444 since 30 Oct 2026 |
| [vxcontrol/pentagi](<https://github.com/vxcontrol/pentagi>) | 15 Oct 2026 | 29,886 | 32,826 | +2,940 (+9.8%) | 184 | +66 since 30 Oct 2026 |
| [Panniantong/Agent-Reach](<https://github.com/Panniantong/Agent-Reach>) | 27 Oct 2026 | 104,122 | 106,933 | +2,811 (+2.7%) | 703 | +478 since 30 Oct 2026 |
| [luongnv89/claude-howto](<https://github.com/luongnv89/claude-howto>) | 23 Oct 2026 | 43,466 | 46,234 | +2,768 (+6.4%) | 346 | +70 since 30 Oct 2026 |
| [nightly-labs/openbot](<https://github.com/nightly-labs/openbot>) | 27 Oct 2026 | 1,697 | 4,275 | +2,578 (+151.9%) | 644 | +240 since 30 Oct 2026 |
| [shiyu-coder/Kronos](<https://github.com/shiyu-coder/Kronos>) | 20 Oct 2026 | 41,840 | 44,249 | +2,409 (+5.8%) | 219 | +162 since 30 Oct 2026 |
| [headroomlabs-ai/headroom](<https://github.com/headroomlabs-ai/headroom>) | 20 Oct 2026 | 76,370 | 78,403 | +2,033 (+2.7%) | 185 | +108 since 30 Oct 2026 |
| [pollen-robotics/microduck](<https://github.com/pollen-robotics/microduck>) | 25 Oct 2026 | 11,154 | 13,186 | +2,032 (+18.2%) | 339 | +69 since 30 Oct 2026 |
| [android/skills](<https://github.com/android/skills>) | 17 Oct 2026 | 8,149 | 10,115 | +1,966 (+24.1%) | 140 | +74 since 30 Oct 2026 |
| [NVIDIA/OpenShell](<https://github.com/NVIDIA/OpenShell>) | 24 Oct 2026 | 18,934 | 20,783 | +1,849 (+9.8%) | 264 | +72 since 30 Oct 2026 |
| [thedotmack/claude-mem](<https://github.com/thedotmack/claude-mem>) (on today's list, #1) | 30 Oct 2026 | 105,064 | 106,688 | +1,624 (+1.5%) | 1,624 | - |
| [gitroomhq/postiz-app](<https://github.com/gitroomhq/postiz-app>) | 27 Oct 2026 | 38,679 | 40,258 | +1,579 (+4.1%) | 395 | +107 since 30 Oct 2026 |
| [vllm-project/vllm](<https://github.com/vllm-project/vllm>) | 21 Oct 2026 | 94,532 | 95,949 | +1,417 (+1.5%) | 142 | +66 since 30 Oct 2026 |
| [SnailSploit/Claude-Red](<https://github.com/SnailSploit/Claude-Red>) | 24 Oct 2026 | 8,623 | 9,957 | +1,334 (+15.5%) | 191 | +91 since 30 Oct 2026 |
| [milind-soni/OpenMausBot](<https://github.com/milind-soni/OpenMausBot>) (on today's list, #2) | 30 Oct 2026 | 7,703 | 8,957 | +1,254 (+16.3%) | 1,254 | - |
| [anthropics/claude-code](<https://github.com/anthropics/claude-code>) | 20 Oct 2026 | 152,763 | 153,998 | +1,235 (+0.8%) | 112 | +100 since 30 Oct 2026 |
| [supabase/supabase](<https://github.com/supabase/supabase>) | 22 Oct 2026 | 113,145 | 114,368 | +1,223 (+1.1%) | 136 | +42 since 30 Oct 2026 |
| [withmarbleapp/os-taxonomy](<https://github.com/withmarbleapp/os-taxonomy>) | 20 Oct 2026 | 6,282 | 7,476 | +1,194 (+19.0%) | 109 | +14 since 30 Oct 2026 |
| [NVIDIA/SkillSpector](<https://github.com/NVIDIA/SkillSpector>) | 27 Oct 2026 | 22,463 | 23,569 | +1,106 (+4.9%) | 276 | +155 since 30 Oct 2026 |
| [alchaincyf/huashu-design](<https://github.com/alchaincyf/huashu-design>) | 27 Oct 2026 | 27,286 | 28,248 | +962 (+3.5%) | 240 | +95 since 30 Oct 2026 |
| [Donchitos/Claude-Code-Game-Studios](<https://github.com/Donchitos/Claude-Code-Game-Studios>) | 30 Oct 2026 | 29,601 | 30,543 | +942 (+3.2%) | 942 | - |
| [mlabonne/llm-course](<https://github.com/mlabonne/llm-course>) | 18 Oct 2026 | 83,959 | 84,805 | +846 (+1.0%) | 65 | +33 since 30 Oct 2026 |
| [twentyhq/twenty](<https://github.com/twentyhq/twenty>) | 22 Oct 2026 | 59,348 | 60,192 | +844 (+1.4%) | 94 | +78 since 30 Oct 2026 |
| [Meloong-Git/PCL](<https://github.com/Meloong-Git/PCL>) | 23 Oct 2026 | 8,777 | 9,470 | +693 (+7.9%) | 87 | +26 since 30 Oct 2026 |
| [coollabsio/coolify](<https://github.com/coollabsio/coolify>) | 26 Oct 2026 | 64,675 | 65,338 | +663 (+1.0%) | 133 | +50 since 30 Oct 2026 |
| [CopilotKit/OpenBot](<https://github.com/CopilotKit/OpenBot>) (on today's list, #4) | 30 Oct 2026 | 8,329 | 8,939 | +610 (+7.3%) | 610 | - |
| [ruvnet/RuView](<https://github.com/ruvnet/RuView>) | 29 Oct 2026 | 101,281 | 101,798 | +517 (+0.5%) | 258 | +159 since 30 Oct 2026 |
| [OpenBMB/VoxCPM](<https://github.com/OpenBMB/VoxCPM>) | 24 Oct 2026 | 40,362 | 40,878 | +516 (+1.3%) | 74 | +49 since 30 Oct 2026 |
| [php/php-src](<https://github.com/php/php-src>) | 23 Oct 2026 | 41,292 | 41,736 | +444 (+1.1%) | 56 | +8 since 30 Oct 2026 |
| [google-gemini/gemini-cli](<https://github.com/google-gemini/gemini-cli>) | 25 Oct 2026 | 108,241 | 108,643 | +402 (+0.4%) | 67 | +19 since 30 Oct 2026 |
| [fastapi/fastapi](<https://github.com/fastapi/fastapi>) | 23 Oct 2026 | 103,901 | 104,299 | +398 (+0.4%) | 50 | +25 since 30 Oct 2026 |
| [macro-inc/macro](<https://github.com/macro-inc/macro>) (on today's list, #7) | 29 Oct 2026 | 5,555 | 5,946 | +391 (+7.0%) | 196 | +283 since 30 Oct 2026 |
| [lightseekorg/tokenspeed](<https://github.com/lightseekorg/tokenspeed>) | 16 Oct 2026 | 2,560 | 2,830 | +270 (+10.5%) | 18 | +4 since 30 Oct 2026 |
| [expo/skills](<https://github.com/expo/skills>) (on today's list, #6) | 29 Oct 2026 | 3,677 | 3,940 | +263 (+7.2%) | 132 | +177 since 30 Oct 2026 |
| [xiaolai/the-craft-of-selfteaching](<https://github.com/xiaolai/the-craft-of-selfteaching>) | 29 Oct 2026 | 18,702 | 18,898 | +196 (+1.0%) | 98 | +40 since 30 Oct 2026 |
| [nodejs/node](<https://github.com/nodejs/node>) | 24 Oct 2026 | 122,952 | 123,126 | +174 (+0.1%) | 25 | +33 since 30 Oct 2026 |
| [aws/agent-toolkit-for-aws](<https://github.com/aws/agent-toolkit-for-aws>) | 25 Oct 2026 | 3,209 | 3,355 | +146 (+4.5%) | 24 | +8 since 30 Oct 2026 |

## Coverage notes

- All 15 listing entries were inspected. Exact primary public GitHub repository metadata and recent releases were checked for all 15 at about 07:01 UTC, and README files for the four picks; all were active and unarchived. Thirteen had an API-detected license; anthropics/skills (licensed per skill, see its card) and togg53192-cmd/jailbreaks had none.
- Ten entries featured in the previous seven days were left out without a material change: thedotmack/claude-mem, milind-soni/OpenMausBot and CopilotKit/OpenBot (30 October), expo/skills and macro-inc/macro (29 October), HKUDS/DeepTutor and obra/superpowers (28 October), JetBrains/thinkrail (26 October), pbakaus/impeccable (25 October) and Renhuai123/ziwei-doushu (24 October). Since those cards they show patch and feature releases, nightly builds or no new release.
- thedotmack/claude-mem released v15.7.0 on 30 October, after yesterday's card. Its notes say that when claude-mem refused a summary from Claude Code, its My Work refresh moved on to the next signed-in agent, which on machines with Codex installed meant hidden Codex runs on the owner's ChatGPT account (about 230 runs in four days in the cited report, issue 5189). The release fixes this and adds security hardening and wider secret redaction. Users of earlier versions with Codex installed may want to update; we note it here rather than repeat the card.
- togg53192-cmd/jailbreaks, a collection of prompts written to override model safety policies, was again not picked: GitHub detects no license, and its purpose is to defeat safeguards rather than to serve as a practical tool.
- Today's listing had no security projects and almost nothing outside AI tooling, so the picks are less varied than usual; we did not reach outside the daily listing to fill that gap.
- The preceding seven calendar dates, 24-30 October, were checked for local history; all seven editions exist.
- The official listing was captured at 08:00:36 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, cost and performance claims are the maintainers' own, including Lightpanda's memory and speed benchmark against headless Chrome and T3 Code's remote-access and usage-data descriptions. No candidate code, installer, plugin, skill or model was installed, downloaded or run, and none of this is a security audit or endorsement.