The week in brief
Behind it, vLLM (+916) and llama.cpp (+853) followed.
Seven new tools joined the directory this week: Diffusers, ComfyUI, XGBoost, scikit-learn and Muse Spark Open (Meta) and 2 more.
On Hacker News, “WhatsApp's help pages hid LLM instructions: dont recommend a regulator” drew the most attention in this space (729 points, 208 comments). Among listed tools, Mistral AI's site was linked from 18 Hacker News stories over the past 90 days, more than any other tool here.
In research, “Focused Omni-Modal GUI Agents” collected the most upvotes on Hugging Face Daily Papers this week (116). Among new GitHub repositories created in the past 28 days, Dreamer-Toby/STEPQuant leads with 101 stars.
Biggest GitHub star gainers
GitHub star counts for the 50 open source tools we track, compared between Oct 13, 2026 and Oct 21, 2026 (186 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| Ollama | 183,020 | 184,125 | +1,105 | 0.60% |
| vLLM | 93,723 | 94,639 | +916 | 0.98% |
| llama.cpp | 131,038 | 131,891 | +853 | 0.65% |
| Whisper | 110,437 | 110,980 | +543 | 0.49% |
| SGLang | 37,085 | 37,561 | +476 | 1.28% |
| Unsloth | 77,936 | 78,352 | +416 | 0.53% |
| Transformers | 167,662 | 167,942 | +280 | 0.17% |
| TensorFlow | 200,922 | 201,154 | +232 | 0.12% |
New listings this week
| Tool | Category | Listed |
|---|---|---|
| Diffusers | ML Frameworks | Oct 17, 2026 |
| ComfyUI | ML Frameworks | Oct 17, 2026 |
| XGBoost | ML Frameworks | Oct 16, 2026 |
| scikit-learn | ML Frameworks | Oct 16, 2026 |
| Muse Spark Open (Meta) | Open Weight Models | Oct 16, 2026 |
| LightGBM | ML Frameworks | Oct 16, 2026 |
| LFM2 / LFM2.5 (Liquid AI) | Open Weight Models | Oct 15, 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.
- Focused Omni-Modal GUI Agents
- PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
- Matrix-Game 4.0: Harnessing Video Models for Real Time Playable Game Worlds
- Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
- S-Agent 2.0: Spatial Reasoning with a General Coding Agent
- The Token Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token
- Large Flow Language Models
- When Do LLMs Help with Feature Selection? A Systematic Empirical Study
- BitMTP: When Multi Token Prediction Meets Low Bit Large Language Models
- OptionWorld: A Benchmark for Diagnosing Failures of LLMs as Long Term Personal Assistants
New GitHub repos in LLM research
Repositories created in the 28 days before Oct 21, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| Dreamer-Toby/STEPQuant | 101 | Python | STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization |
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.