The week in brief
Behind it, Firecrawl (+2,710) and vLLM (+1,502) followed.
One new tool joined the directory this week: NVIDIA OpenShell.
On Hacker News, “OpenShell. A safe, private runtime for fleets of autonomous AI agents” drew the most attention in this space (502 points, 218 comments). Among listed tools, OpenRouter's site was linked from 37 Hacker News stories over the past 90 days, more than any other tool here.
In research, “IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems” collected the most upvotes on Hugging Face Daily Papers this week (101). Among new GitHub repositories created in the past 7 days, Charonyuu/whatsmyagentdoing leads with 242 stars.
Biggest GitHub star gainers
GitHub star counts for the 54 open source tools we track, compared between Oct 18, 2026 and Oct 26, 2026 (180 hours apart).
| Tool | Stars before | Stars after | Gain | Change |
|---|---|---|---|---|
| OpenCode | 216,488 | 221,720 | +5,232 | 2.42% |
| Firecrawl | 192,754 | 195,464 | +2,710 | 1.41% |
| vLLM | 94,074 | 95,576 | +1,502 | 1.60% |
| OpenAI Codex | 129,755 | 130,977 | +1,222 | 0.94% |
| Claude Code | 152,248 | 153,418 | +1,170 | 0.77% |
| Ollama | 183,742 | 184,823 | +1,081 | 0.59% |
| Gemini CLI | 107,440 | 108,397 | +957 | 0.89% |
| Dify | 158,807 | 159,581 | +774 | 0.49% |
New listings this week
| Tool | Category | Listed |
|---|---|---|
| NVIDIA OpenShell | Dev Tools & Protocols | Oct 23, 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.
- IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
- UserArena: Benchmarking Interactive User Simulation for Long Horizon Shopping Agents
- FilmFlow: Agentic System for 3D Virtual Film Cinematography
- HiSTEVE 1.0: Harnessing Human Interface VLA Agents for Open World Games
- RSIHub: A Composable Framework for Agent Evolution Methods
- SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
- Do "True" and "False" Add Up to One? Complement Consistency in LLM Agent Opinion Simulations
- J-Comm: Jacobian-Guided Latent Communication between LLM Agents
- Reimagining Enterprise RAG for Multi Agent Systems: A Knowledge Layer That Organizes Before It Retrieves
- Frontier-OPD: Discovering the Edge of Agent Capability and Teaching Agents to Go Beyond
New GitHub repos in AI agents
Repositories created in the 7 days before Oct 26, 2026, ranked by stars.
| Repository | Stars | Language | Description |
|---|---|---|---|
| Charonyuu/whatsmyagentdoing | 242 | JavaScript | See what every Claude Code and Codex agent on your machine is doing: live, in a little office. |
| Zafer-Liu/claude-super-sidebar | 155 | JavaScript | A visual sidebar for Claude Code and Codex: agent trees, live status, and conversation task flows. |
| Cattmonkey/ChaosIntelligence | 141 | Python | 把智能体当函数，把想法写成程序。Agent native functional language with a CLI, Web IDE, goal driven bots and live UI. Source available; no AI training. |
| Monopoly0024/simple-reviewer-v1 | 136 | Python | Simple Reviewer: a Codex skill for AI assisted coding and Vibe Coding. Explain code, visualize workflows, and verify goals with evidence. | 简单的审阅者：协助 AI 编程与 Vibe Coding，解释代码、可视化流程，以证据复核目标。 |
| mokevnin/dev-quality-gates | 114 | Python | An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits. |
| stockedge/manga-generator | 113 | JavaScript | 原作から脚本・画像生成・組版・PDF出力まで進める、Codex向け漫画制作ツール |
| YOLOW92/pagesift | 94 | Rust | High performance, memory efficient Rust web crawler & content extraction engine for AI agents and RAG. Adaptive crawling, clean Markdown, structured data, PDF/RSS parsing, browser rendering, Firecrawl |
| hassan-algo/open-sesame | 93 | HTML | 🔓 An AI web pentest skill for Claude Code. Point it at a site you're authorized to test. It maps the attack surface, works through the OWASP WSTG, validates findings, and writes dev + stakeholder rep |
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 Drydock. Numbers are shown as recorded; if a figure is unavailable, it is left out rather than estimated.