The week in brief
Behind it, ComfyUI (+1,633) and Ollama (+1,005) followed.
Seven new tools joined the directory this week: Open WebUI, Kimi K3 (Moonshot AI), Qwen3.8 Flash Next, Ripple (Ricursive) and KTransformers and 2 more.
On Hacker News, “Ripple-65B Preview: U.S. Open Weight SOTA on Agentic Coding” drew the most attention in this space (341 points, 127 comments). Among listed tools, Mistral AI's site was linked from 24 Hacker News stories over the past 90 days, more than any other tool here.
In research, “From Autonomous Agents to Cognitive Symbionts: Toward AI Augmented Human Intelligence” collected the most upvotes on Hugging Face Daily Papers this week (119). Among new GitHub repositories created in the past 28 days, aa1143/NamiGPT leads with 209 stars.
Biggest GitHub star gainers
GitHub star counts for the 57 open source tools we track, compared between Oct 31, 2026 and Nov 9, 2026 (214 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| Strata | 36,738 | 42,275 | +5,537 | 15.07% |
| ComfyUI | 144,265 | 145,898 | +1,633 | 1.13% |
| Ollama | 185,428 | 186,433 | +1,005 | 0.54% |
| Unlimited OCR | 30,060 | 31,000 | +940 | 3.13% |
| llama.cpp | 132,935 | 133,800 | +865 | 0.65% |
| Whisper | 111,630 | 112,280 | +650 | 0.58% |
| vLLM | 95,961 | 96,593 | +632 | 0.66% |
| MOSS-Image (OpenMOSS) | 2,331 | 2,763 | +432 | 18.53% |
New listings this week
| Tool | Category | Listed |
|---|---|---|
| Open WebUI | ML Frameworks | Nov 08, 2026 |
| Kimi K3 (Moonshot AI) | Open Weight Models | Nov 07, 2026 |
| Qwen3.8 Flash Next | Open Weight Models | Nov 06, 2026 |
| Ripple (Ricursive) | Open Weight Models | Nov 05, 2026 |
| KTransformers | ML Frameworks | Nov 03, 2026 |
| GLM (Z.ai) | Open Weight Models | Nov 03, 2026 |
| Nanbeige | Open Weight Models | Nov 02, 2026 |
Most discussed on Hacker News
The highest scoring Hacker News stories in this space during the week.
| Story | Points | Comments | Discussion |
|---|---|---|---|
| Ripple-65B Preview: U.S. Open Weight SOTA on Agentic Coding | 341 | 127 | thread |
| LLMs are not superhuman at reading and writing neural network weights | 151 | 23 | thread |
| Show HN: Uncracked City, detective game where you question LLM suspects that lie | 127 | 69 | thread |
| Memorilla: Latent Semantic Memory for LLMs | 124 | 13 | thread |
| Why I will not be using LLMs in my coding | 115 | 231 | thread |
| Agentic backdoors via pretraining poisoning | 109 | 31 | 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.
- From Autonomous Agents to Cognitive Symbionts: Toward AI Augmented Human Intelligence
- VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
- SLA: Scaling Spatial-Language-Action Model via Continual Pretraining
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
- SplatAnything: Gaussian Spacing Normalization for Feed forward 3DGS across Arbitrary Scenes
- Generative Latent Priors for Interpreting and Steering Protein Language Models
- Are These Programmers Ripe Enough to Eat? Evaluating How LLMs Handle Lexical Knowledge Conflicts in Translation
- ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models
- Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents
- One Run Is Not Enough: A Monte Carlo Protocol for Evaluating LLM Reliability on Data Science Tasks
New GitHub repos in LLM research
Repositories created in the 28 days before Nov 09, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| aa1143/NamiGPT | 209 | 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 |
| Toyhom/awesome-computational-character-modeling | 204 | TeX | Survey companion for Computational Character Modeling: role playing methods, data foundations, and evaluation, organized by the manuscript. |
| didilili/mianstack | 143 | JavaScript | 🚀 面栈 MianStack｜程序员面试题库天花板！Java、Python、数据库、算法、大模型、AI Agent、RAG 一栈备齐。真实面经关联高频考点，按公司、岗位定向备考；图文题解、精华专题、项目源码拆解，全系标配。面试官出题，面栈出招！免费开源，持续更新。 |
| OmniJev/Flide | 100 | Python | 🔥🔥 The extremely fast inference engine for decision model |
| Mafdet-AI/mafdet | 80 | Python | You type. It already knows. Local LLMs that read and think while you type. |
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.