The week in brief
Behind it, VoiceInk (+64) and Reflect Open (+14) followed.
Four new tools joined the directory this week: writenode, Orkas, Clean Email and AI Book Studio (Bookfolio).
On Hacker News, “Survival LLM: AI assistant and emergency library that runs on your own computer” drew the most attention in this space (543 points, 204 comments). Among listed tools, ChatGPT's site was linked from 34 Hacker News stories over the past 90 days, more than any other tool here.
In research, the newest arXiv paper in our feed is “Is That Clear? The Impacts of Clarifying Questions on Human LLM Interaction”. Among new GitHub repositories created in the past 14 days, modelflare-ai/AnyModelBot leads with 2,100 stars.
Biggest GitHub star gainers
GitHub star counts for the 6 open source tools we track, compared between Oct 27, 2026 and Nov 3, 2026 (169 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| Handy | 34,841 | 37,248 | +2,407 | 6.91% |
| VoiceInk | 6,939 | 7,003 | +64 | 0.92% |
| Reflect Open | 1,597 | 1,611 | +14 | 0.88% |
| wallabag | 13,031 | 13,042 | +11 | 0.08% |
| Read Aloud | 1,786 | 1,791 | +5 | 0.28% |
New listings this week
| Tool | Category | Listed |
|---|---|---|
| writenode | Notes & Knowledge | Oct 31, 2026 |
| Orkas | Personal Assistants | Oct 31, 2026 |
| Clean Email | Oct 31, 2026 | |
| AI Book Studio (Bookfolio) | Writing | Oct 31, 2026 |
Most discussed on Hacker News
The highest scoring Hacker News stories in this space during the week.
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.
- Is That Clear? The Impacts of Clarifying Questions on Human LLM Interaction
- When History Overrides Intent: Relational Schema Lock-In in Human LLM Interaction
- Nedimo: An Evidence-Grounded Multilingual Pipeline for AI Generated Sleep Stories
- Assessing AI Companion Chatbot Safety for Vulnerable Users: A Crisis-Stage Multi Platform Evaluation
- Evaluating Conversational Explainability in Healthcare: Comparing the Explainability Assistant and a Traditional XAI Dashboard
New GitHub repos in AI assistant
Repositories created in the 14 days before Nov 03, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| modelflare-ai/AnyModelBot | 2,100 | Python | 🤖 Open source, local first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. |
| t8y2/motty | 546 | Go | SSH, SFTP, port forwarding, VNC/RDP and an AI assistant、MCP in one native window: a Go desktop app built on Viva, with no webview. |
| victorgassuncao21/piper-morgan-assistant | 58 | HTML | Piper Morgan Product: Intelligent Product Management Assistant for Python |
| ishangautam7/Talvio | 52 | Rust | Talk to your computer: dictation into any app, a voice assistant that answers out loud and gets things done, meeting notes, and a phone app to control your PC. Local first, open source. |
| kaanarici/Emblem | 31 | Swift | An iPhone assistant that answers with native SwiftUI pages |
| mazulo/leis-mcp | 26 | Python | Servidor MCP para buscar e citar a legislação brasileira no Claude e em qualquer assistente de IA: texto exato de 1,2 milhão de normas (CF, CLT, CDC, Código Civil, LGPD…), com fonte oficial e avisos d |
| yimengbenxin/Personal-AI-OS | 26 | TypeScript | Personal AI OS (Personal Agent) · Yimi (依米): your own self hosted personal AI assistant across phone, glasses, watch and Mac · 每个人自己的依米 |
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.