The week in brief
Behind it, ComfyUI (+1,343) and Ollama (+812) followed.
Four new tools joined the directory this week: Nanbeige, Unlimited OCR, Mistral Large 4 and LFM3 (Liquid AI).
On Hacker News, “LLM Voice” drew the most attention in this space (609 points, 336 comments). Among listed tools, Mistral AI's site was linked from 23 Hacker News stories over the past 90 days, more than any other tool here.
In research, “Wave Forcing: Towards Speed-of-Light Streaming Video Generation” collected the most upvotes on Hugging Face Daily Papers this week (82). Among new GitHub repositories created in the past 28 days, aa1143/NamiGPT leads with 176 stars.
Biggest GitHub star gainers
GitHub star counts for the 53 open source tools we track, compared between Oct 27, 2026 and Nov 3, 2026 (169 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| Strata | 34,163 | 38,884 | +4,721 | 13.82% |
| ComfyUI | 143,444 | 144,787 | +1,343 | 0.94% |
| Ollama | 184,957 | 185,769 | +812 | 0.44% |
| llama.cpp | 132,501 | 133,250 | +749 | 0.57% |
| vLLM | 95,675 | 96,207 | +532 | 0.56% |
| MOSS-Image (OpenMOSS) | 2,056 | 2,537 | +481 | 23.39% |
| Whisper | 111,372 | 111,853 | +481 | 0.43% |
| Unsloth | 78,616 | 78,997 | +381 | 0.48% |
New listings this week
| Tool | Category | Listed |
|---|---|---|
| Nanbeige | Open Weight Models | Nov 02, 2026 |
| Unlimited OCR | Open Weight Models | Oct 31, 2026 |
| Mistral Large 4 | Open Weight Models | Oct 30, 2026 |
| LFM3 (Liquid AI) | Open Weight Models | Oct 29, 2026 |
Most discussed on Hacker News
The highest scoring Hacker News stories in this space during the week.
| Story | Points | Comments | Discussion |
|---|---|---|---|
| LLM Voice | 609 | 336 | thread |
| Survival LLM: AI assistant and emergency library that runs on your own computer | 543 | 204 | thread |
| Sleep framework: A new way for LLMs to retain knowledge in continual learning | 273 | 58 | thread |
| Malware uses LLMs to rank victims by how much they're worth | 261 | 137 | thread |
| Show HN: I Turned DOOM into a Transformer | 132 | 36 | thread |
| Agentic backdoors via pretraining poisoning | 101 | 30 | 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.
- Wave Forcing: Towards Speed-of-Light Streaming Video Generation
- Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self Improvement
- CoworkOS:Scaling Agent Coworkers for Real world Automation
- CUA-Master: Scaling Computer use Agents through Open World Recursive Improvements
- Democratizing Robot-Use Agents: A Unified Harness with Open Models
- Pretraining Data Scale Reverses the Muon-AdamW Fine Tuning Gap
- Tracing the Scientific Discovery Capacity of LLMs to Their Training Data
- A Scaling Theory of Multi-Epoch Pretraining: Late-Time Overfitting and Ensembling
- Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text to SQL
- Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
New GitHub repos in LLM research
Repositories created in the 28 days before Nov 03, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| aa1143/NamiGPT | 176 | Python | 零基础入门大模型（LLM）的基础教程：从零手写 GPT-2，一行行看懂大模型是怎么工作的 | Build GPT-2 from scratch in PyTorch, step by step |
| TheLastOxygen/mafdet | 79 | Python | You type. It already knows. Local LLMs that read and think while you type. |
| Toyhom/awesome-computational-character-modeling | 67 | TeX | Survey companion for Computational Character Modeling: role playing methods, data foundations, and evaluation, organized by the manuscript. |
| AllSpark-Research/Vela | 32 | Vela: User Behavior as Supervision Sparks LLM Intelligence (official paper, task templates, and prompts from AllSpark at Xiaohongshu). |
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 Axiomi. Numbers are shown as recorded; if a figure is unavailable, it is left out rather than estimated.