Tools Bench.

Product launches and open-source repos with enough signal to earn a second look.

Last Brew Time: Jun 14, 2026, 7:27 AM PT

Insight

The most-loved tools this run aren't agents at all but one-prompt creation engines, each collapsing a whole production pipeline into a single text box

01.WEBSITES

02.3D ASSETS

03.CHARACTER VIDEO

04.MUSIC

Featured

GitHub4.9K

NVIDIA/SkillSpector

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

youtube
SkillSpector: NVIDIA's Open Source Scanner For Malicious Agent Skills

Market Signal

Why It Has Market Pull

NVIDIA's open-source scanner for AI agent skills inspects a skill for prompt injection, data exfiltration, and supply-chain risk before you install it, and it has caught on fast: roughly 5,000 GitHub stars within weeks of its May 2026 release and integration into OpenClaw's skill-review pipeline. For any team that installs third-party agent skills, it is an unusually credible early entrant worth a closer look.

  • ~5,000 GitHub stars and 383 forks within weeks of the May 22, 2026 release; reached GitHub trending
  • Detects 64 vulnerability patterns across 16 categories (prompt injection, data exfiltration, tool poisoning, supply-chain risk) via hybrid static plus LLM analysis
  • Already wired into OpenClaw's ClawHub publishing flow as an advisory security check
  • Backed by the NVIDIA organization; Apache-2.0 licensed, with terminal, JSON, Markdown, and SARIF output and Docker deployment
  • Grounded in NVIDIA's study of 42,447 real agent skills, which found 26% contained a vulnerability and 5% showed likely malicious intent

feedbacks

What People Are Saying

  • "A good security plan needs multiple layers, this seems like a good one to include."HN comment

  • "Skills are ultimately just prompts, and agents execute code based on what is in them."HN comment

  • "Skills can include python files that do whatever in subfolders."HN comment

  • "LLM reviewing LLM? If the review model catches it, the executing model would refuse to run it."HN comment

  • "It combines static checks with AI-assisted semantic analysis to flag risks malware scanners miss."Dev.to article

  • "It might be better than nothing, but it is hard to know how much better."HN comment

  • "26% of AI agent skills are dangerous, and SkillSpector by NVIDIA is the fix."YouTube post

Product Hunt311

Kimi K2.7 Code

Kimi K2.7 Code is Moonshot AI’s latest coding-focused agentic model, built for long-horizon software engineering, 256K context, multi-step tool use, multimodal inputs, and around 30% lower reasoning-token usage than K2.6. Available in Kimi Code, Kimi API, and as open weights/code.

youtube
Kimi K2.7 Code Is HERE - Is THIS the Best Open Coding Model Yet?

Market Signal

Why It Has Market Pull

Kimi K2.7 Code is Moonshot AI's newest open-weights coding model, built for long-horizon software work with a 256K context, multi-step tool use, and roughly 30% lower reasoning-token use than its predecessor, at a price up to about 12x below the leading closed models. It arrives from a lab that just raised about $2B at a ~$20B valuation, and early adoption is real, with 15,000+ downloads in its first month.

  • Moonshot AI raised ~$2B at a ~$20B valuation (May 2026), backed by Alibaba, Tencent, and China Mobile, with reported ARR over $200M
  • 15,145 first-month downloads and 585 likes on Hugging Face; released under a modified-MIT license allowing commercial use
  • Priced at $0.95 per million input and $4.00 per million output tokens, up to ~12x cheaper than leading closed coding models
  • Beats Claude Opus 4.8 on the MCPMark Verified tool-use benchmark (81.1 vs 76.4) per the vendor, with ~30% fewer reasoning tokens than K2.6
  • Reached #2 product of the day on Product Hunt (~316 upvotes); 256K context, multimodal input, 1T-parameter mixture-of-experts

feedbacks

What People Are Saying

  • "Switched to Kimi and it solved my problem in less than 60 seconds, I was hooked."HN comment

  • "Better than Gemini 2.5 Pro on tool calling."HN comment

  • "The 30% drop in reasoning tokens alongside better multi-step success is the interesting signal here."Product Hunt comment

  • "Love seeing the focus shift from benchmark chasing to real-world coding workflows."Product Hunt comment

  • "This time the benchmarks are a bit below my expectations, only slightly better than 2.6."Product Hunt comment

  • "Do you have evals that measure whether it can backtrack from a failed test run?"Product Hunt comment

  • "The best open-source coding agent available today for tool-integrated workflows."Dev.to article

Product Hunt217

Prometheus by Firecrawl

An experimental Forward Deployed Agent for web data from Firecrawl. Describe the web data you need and it writes Firecrawl code to collect it. Run it yourself or let us host and automatically maintain it as pages change.

Market Signal

Why It Has Market Pull

Prometheus is Firecrawl's new agent for web data: describe the data you want in plain English and it writes verified collector code you can run yourself or let Firecrawl host and self-heal as pages change. It comes from a well-funded category leader, Firecrawl, whose data infrastructure already powers pipelines at Apple, Canva, Shopify, and Zapier, which makes this experimental launch worth tracking.

  • Parent company raised a $14.5M Series A (Aug 2025) led by Nexus Venture Partners, with Y Combinator and Shopify's CEO participating
  • Firecrawl's core open-source repo carries ~133,000 GitHub stars and ~7,800 forks
  • Production users include Apple, Canva, Shopify, Zapier, and Replit, with 350,000+ developers signed up
  • Prometheus reached the top 3 of its Product Hunt launch day with ~217 upvotes
  • Still labeled experimental, and the most common user critique of Firecrawl remains per-page cost

feedbacks

What People Are Saying

  • "This would have been an entire startup a few years ago just to scrape a site reliably, now it is an API call away."Product Hunt comment

  • "For the first time I'm able to reliably extract meaningful data from unstructured web content."Product Hunt comment

  • "This will save us several hours every month that would otherwise go into manual research."Product Hunt comment

  • "I'm getting much better results from Firecrawl, not affiliated, just a happy customer."HN comment

  • "We currently use Firecrawl for our crawling infrastructure."HN comment

  • "Firecrawl is egregiously expensive."HN comment

  • "Simple way to turn websites into markdown, and it handles PDFs as well."Product Hunt comment

Sources

GitHub

freeCodeCamp/freeCodeCamp

447.0K

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

iptv-org/iptv

120.1K

Collection of publicly available IPTV channels from all over the world

cypress-io/cypress

49.8K

Fast, easy and reliable testing for anything that runs in a browser.

GorvGoyl/Clone-Wars

35.2K

100+ open-source clones of popular sites like Airbnb, Amazon, Instagram, Netflix, Tiktok, Spotify, Whatsapp, Youtube etc. See source code, demo links, tech stack, github stars.

Product Hunt

Vercel Drop

406

Vercel Drop lets you deploy a file or folder by dragging it into your browser. You don't need Git, the Vercel CLI, or any local setup. Drop a project onto vercel.com/drop, pick a team and project name, and select Deploy. Vercel will create a new project, upload your files, and publish them straight to production with a live URL you can share. All in a matter of seconds.

CakewordAI

187

Kids point the camera at anything — a cup, a teddy bear, a guitar — and Cakeword cuts it out into a sticker, says its name in the language they're learning, and adds it to their Word Dex. 100% on-device AI. No accounts, no ads, no data collection.

NomNak

146

NomNak helps you find restaurants through people you trust. See where your friends actually eat, save spots to try, and build a Food Passport of everywhere you’ve been.

Avatars in ElevenCreative

131

The best AI voices, now with a face. Create studio-grade talking videos from a script, a voice, and an avatar - all in one place.

Feezza

16

Feezza is the app. Fiza is your AI companion inside it. Most apps tell you what you ate. Fiza tells you why it matters. Hidden calorie detection from cooking methods. Medication interaction warnings using NIH live database. 26 chronic conditions with ADA and AHA clinical targets. Doctor-ready health reports. Condition flare prediction. Emergency alerts. Pattern recognition across weeks not just today. 5M+ foods. The only AI companion that connects what you eat to how you feel.

ScrollJail

14

Every time you open a distracting app, an AI bouncer stops you and asks: Why are you here? Good reason: you're in. Bad reason: you're not. No paywall, no guilt-trip onboarding. Just an AI that won't let you lie to yourself. Free iOS Shortcut, 3 min setup.

Hacker News

Extend UI – open-source UI kit for modern document apps

249 pts

We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully customizable. Demo video here: https://share.extend.ai/kRmSGKRF When we started, we tried every file viewer and document component library we could find. Unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for https://extend.ai/ . It was only ever meant to be... (249 points, 80 comments).

I am building a map of people who lived in the Roman Empire

186 pts

Driving home from work one day, I wanted to know how many people we knew the names of who lived during the Roman era. Searching around, I found lists of Consuls and officials, but nothing that covered ordinary people or even most people like freedmen and slaves. So I ended up building a pipeline to process the more than 500k Latin inscriptions in the Epigraphic Database Clauss-Slaby https://edcs.hist.uzh.ch/en/ and extract the names of people (and attempt to cluster them, but this is a work in p... (186 points, 43 comments).

Paca – Lightweight Jira alternative for human-AI collaboration

158 pts

I built Paca out of pure passion—a free and lightweight Jira alternative written in Go where humans and AI agents work together as equal teammates to plan sprints and assign tasks to each other. It is fully customizable with custom views, fields, and a WASM-based plugin architecture. My team uses it daily for our own development, so it will be continuously maintained and completely free forever (158 points, 56 comments).

On-device transcriber that's 97% accurate at identifying speakers

32 pts

I’ve spent the last seven months building a tool I wish I’d had in my previous roles. MimicScribe is a macOS menu bar app that fits the "AI notetaker" category. It has accurate on-device speaker identification (a first possibly?), real-time meeting talking points for discovery calls, and a fully keyboard- and voice-driven interface. I believe the accuracy of the speaker ID system is its biggest strength. I used fluid audio’s port of ( https://github.com/fluidInference/FluidAudio ) Pyannote's com... (32 points, 10 comments).

Prisma Next – data contracts, migration graphs, agent DX

13 pts

Hey I'm Will from the Prisma team, engineering manager and also the lead developer on Prisma Next. I'd like to introduce you all to the next version of Prisma: a full rewrite in TypeScript that builds on the established patterns in Prisma and comes with a family of skills that integrate it into whatever AI tooling you're using in 2026. (Read the announcement on our blog here: https://pris.ly/pn-ea ) The three topics in the title are brand new concepts in Prisma Next so let me give you a quick ru... (13 points, 2 comments).

HF Spaces

DeepSite v4

16.6K likes

Generate any application by Vibe Coding it DeepSite is a Vibe Coding Platform designed to make coding smarter and more efficient. Tailored for developers, data scientists, and AI engineers, it integrates generative AI into your coding projects to enhance creativity and productivity. DeepSite v4 is a Hugging Face Space tagged with docker, region:us. It has 16617 likes on Hugging Face.

Open LLM Leaderboard

14.0K likes

Track, rank and evaluate open LLMs and chatbots Modern React interface for comparing Large Language Models (LLMs) in an open and reproducible way. 📊 Interactive table with advanced sorting and filtering 🔍 Semantic model search 📌 Pin models for comparison 📱 Responsive and modern interface 🎨 Dark/Light mode ⚡️ Optimized performance with virtualization The project is split into two main parts: React Material-UI TanStack Table & Virtual Express.js FastAPI Hugging Face API Docker The application is containerized using Docker and can be run using: Open LLM Leaderboard is a Hugging Face Space tagged with docker, leaderboard, modality:text, submission:automatic, test:public. It has 14020 likes on Hu...

AI Comic Factory

11.1K likes

Create your own AI comic with a single prompt Last release: AI Comic Factory 1.2 The AI Comic Factory has an official website: aicomicfactory.app For more information about my other projects please check linktr.ee/FLNGR. If you like the AI Comic Factory, let me know! I am always creating new spaces and exploring new ideas for demos, meaning I don't have much time to take care of all of them (I wish I could clone myself or ask robots to do it). If you appreciate the AI Comic Factory and would like to leave a tip, that would be very kind 🫶 First, I would like to highlight that everything is open-source (see here, here, here, here). However the project isn't a monolithic Space that can be dupli...

Kolors Virtual Try-On

10.1K likes

Kolors Virtual Try-On is a Hugging Face Space tagged with gradio, region:us. It has 10105 likes on Hugging Face.

Wan2.2 Animate

5.1K likes

Wan2.2 Animate is a Hugging Face Space tagged with gradio, region:us. It has 5118 likes on Hugging Face.

MusicGen

5.1K likes

AudioCraft is a PyTorch library for deep learning research on audio generation. AudioCraft contains inference and training code for two state-of-the-art AI generative models producing high-quality audio: AudioGen and MusicGen. Installation AudioCraft requires Python 3.9, PyTorch 2.0.0. To install AudioCraft, you can run the following: We also recommend having ffmpeg installed, either through your system or Anaconda: At the moment, AudioCraft contains the training code and inference code for: MusicGen: A state-of-the-art controllable text-to-music model. AudioGen: A state-of-the-art text-to-sound model. EnCodec: A state-of-the-art high fidelity neural audio codec. Multi Band Diffusion: An EnC...

AI Tools — June 14, 2026 Edition | Agentic Brew