The week in brief
Behind it, Browser Use (+503) and GPT Researcher (+111) followed.
On Hacker News, “Show HN: Let your AI agents paint big arrows, boxes and text on your screen” drew the most attention in this space (416 points, 196 comments). Among listed tools, Claude's site was linked from 40 Hacker News stories over the past 90 days, more than any other tool here.
In research, “DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models” collected the most upvotes on Hugging Face Daily Papers this week (147). Among new GitHub repositories created in the past 7 days, LosaLosSantos/aurelio-finance leads with 2,612 stars.
Biggest GitHub star gainers
GitHub star counts for the 16 open-source tools we track, compared between Oct 5, 2026 and Oct 12, 2026 (155 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| OpenHands | 90,059 | 90,689 | +630 | 0.70% |
| Browser Use | 117,209 | 117,712 | +503 | 0.43% |
| GPT Researcher | 29,924 | 30,035 | +111 | 0.37% |
| garak | 9,439 | 9,532 | +93 | 0.99% |
| Inspect | 2,943 | 2,986 | +43 | 1.46% |
| STORM | 31,573 | 31,611 | +38 | 0.12% |
| NeMo Guardrails | 7,246 | 7,280 | +34 | 0.47% |
| Guardrails AI | 7,489 | 7,511 | +22 | 0.29% |
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.
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
- S-Space: Exploring Spatial Workspace in Multimodal Language Models
- Reflex: Visually Grounded Reactive Humanoid Control
- SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
- EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
- RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
- X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
- SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
- MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents
- OpenPA: Forced-alignment-free Multi-granular Pronunciation Assessment with Mixed-transcript Adaptation
New GitHub repos in LLM
Repositories created in the 7 days before Oct 12, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| LosaLosSantos/aurelio-finance | 2,612 | Python | Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer. |
| NousResearch/hermes-official-plugins | 216 | Python | ☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog. |
| Ayzzz123/mcd-coupon-strategist | 177 | Python | 麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案，并主动提示凑单陷阱。 |
| lawrencewzen/wx-bot | 119 | TypeScript | 把微信接入你的 AI Agent（Grok / Muse / Claude 等）· Connect WeChat to your personal AI agent via official iLink |
| VecSzn/PolyStrata | 99 | C++ | Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost, image input. Built o |
| deeplethe/fde-gym | 92 | TypeScript | The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live. |
| onehumanbeing/esp32-iphone-agent | 82 | Python | Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No developer account, no Xcode, no jailbreak. |
| HRuiCcc/RuiC-oc-ferry | 76 | JavaScript | 把 OpenCode 的免费模型摆渡给 WorkBuddy —— 隔离运行时、并发检测、判定缓存、一键导入、本机 OpenAI 兼容转发口 |
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 Intelsi. Numbers are shown as recorded; if a figure is unavailable, it is left out rather than estimated.