The week in brief
Behind it, VoiceInk (+74) and Reflect Open (+12) followed.
11 new tools joined the directory this week: Semantic Scholar, Scite, ResearchRabbit, Perplexity and Elicit and 6 more.
On Hacker News, “Swedish government offices to ban ChatGPT and Claude” drew the most attention in this space (322 points, 124 comments). Among listed tools, ChatGPT's site was linked from 33 Hacker News stories over the past 90 days, more than any other tool here.
In research, the newest arXiv paper in our feed is “Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox”. Among new GitHub repositories created in the past 7 days, victorgassuncao21/piper-morgan-assistant leads with 58 stars.
Biggest GitHub star gainers
GitHub star counts for the 5 open source tools we track, compared between Oct 18, 2026 and Oct 26, 2026 (180 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| Handy | 34,095 | 34,696 | +601 | 1.76% |
| VoiceInk | 6,853 | 6,927 | +74 | 1.08% |
| Reflect Open | 1,584 | 1,596 | +12 | 0.76% |
| wallabag | 13,017 | 13,027 | +10 | 0.08% |
New listings this week
| Tool | Category | Listed |
|---|---|---|
| Semantic Scholar | Research | Oct 24, 2026 |
| Scite | Research | Oct 24, 2026 |
| ResearchRabbit | Research | Oct 24, 2026 |
| Perplexity | Research | Oct 24, 2026 |
| Elicit | Research | Oct 24, 2026 |
| Consensus | Research | Oct 24, 2026 |
| Apple Creator Studio | Writing | Oct 24, 2026 |
| Read Aloud | Voice & Audio | Oct 23, 2026 |
| Gemini in Google Docs | Writing | Oct 22, 2026 |
| Zoom My Notes | Meetings | Oct 21, 2026 |
| Notion Calendar | Scheduling & Tasks | Oct 21, 2026 |
Most discussed on Hacker News
The highest scoring Hacker News stories in this space during the week.
| Story | Points | Comments | Discussion |
|---|---|---|---|
| Swedish government offices to ban ChatGPT and Claude | 322 | 124 | thread |
| Show HN: Qwen3-4B with the AI writing tics trained out | 158 | 113 | thread |
| On AI writing | 96 | 62 | thread |
Listed tools with the most Hacker News links
Hacker News stories linking to each tool's own website over the past 90 days.
Notable new papers
The most upvoted papers on Hugging Face Daily Papers and the newest relevant arXiv preprints from this week.
- Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox
- Beyond Correctness: How Novice Software Engineering Students Exercise Oversight of Generative AI
- Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration
- In Browser Human AI Co-Writing for Counterspeech: An Exploratory User Study of Agency, Perceived Response Quality, and Time
- Making Generative AI Workable at Work: Accountability, Localization, and Representation in Kenyan and Nigerian Small Businesses
New GitHub repos in AI assistant
Repositories created in the 7 days before Oct 26, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| victorgassuncao21/piper-morgan-assistant | 58 | HTML | Piper Morgan Product: Intelligent Product Management Assistant for Python |
| zickrian/isle | 53 | Rust | A notch style island for GNOME with an AI assistant that installs and fixes things, Claude Code and Codex approvals from the notch, music with synced lyrics, notifications, a focus timer, tasks and a |
| yqf66/Solevia | 41 | Python | Solevia · 足下：能聊清需求、规划路线、陪你执行的智能规划助手。节奏型、探索型、期限型规划，覆盖学习、生活与技术成长。 |
| kaanarici/Emblem | 29 | Swift | An iPhone assistant that answers with native SwiftUI pages |
How we compile this report
Every figure comes from a public source: star counts from the GitHub API, story scores and links from Hacker News (via Algolia), papers from arXiv and Hugging Face Daily Papers, and new repositories from GitHub search. Hacker News link counts include stories whose link points to the tool's own domain. Listing dates are the day a tool joined Ryza. Numbers are shown as recorded; if a figure is unavailable, it is left out rather than estimated.