Tools Bench.

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

Last Brew Time: Jul 19, 2026, 10:37 AM PT

Insight

The tools with the loudest public applause in this run have mostly stopped shipping, proving like counts are a lagging indicator of momentum

01.DORMANT CROWD-PLEASERS

02.A VIDEO LAB PAUSED UNDER ITS OWN DEMAND

03.QUIETLY-SHIPPING AGENT INFRASTRUCTURE NOBODY IS HYPING

Featured

GitHub20.2K

trycua/cua

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

youtube
Cua — Open-Source Infrastructure for Computer-Use Agents

Market Signal

Why It Has Market Pull

Cua is a Y Combinator-backed open-source infrastructure project for computer-use agents with strong, sustained GitHub growth, a well-received public launch, and credible independent commentary calling it durable infrastructure rather than a weekend hack.

  • Roughly 18-20k GitHub stars, growing at a reported 1,300+ stars per week
  • Y Combinator batch company, founded by engineers with backgrounds spanning Microsoft/Xbox AI work
  • Launch discussion on Hacker News scored 172 points with 73 comments
  • Reported early seed funding in the low hundreds of thousands (aggregator-sourced, not confirmed via primary press release)
  • 226 open GitHub issues and an active release cadence, most recently in mid-July 2026

feedbacks

What People Are Saying

  • "Congrats on the launch! I don't know if this is a problem you've faced, but I'm curious: how do LLM tool devs handle authn/authz?"HN comment

  • "it opened a MacOS VM and started to do stuff, but it got ahead of itself and starting typing things in the wrong place."HN comment

  • "We still recommend pairing the Omni loop configuration with a more capable VLM, such as Qwen2.5-VL 32B, or using cloud LLM providers like Sonnet 3.7."HN comment

  • "Would love to use this for TestDriver, but needs to support Windows"HN comment

  • "in the small group of agent-infrastructure projects that look like they'll still matter in 18 months"tech blog

  • "Some Keyboard Keys (;, ., etc.) Not Functioning Properly in Virtual Machine"GitHub issue

GitHub9.8K

MoonshotAI/kimi-cli

Kimi Code CLI is your next CLI agent.

youtube
Kimi CLI: First Look: Fast Setup & Real Repo Demo

Market Signal

Why It Has Market Pull

Kimi CLI is a terminal coding agent from Moonshot AI, a well-funded, high-profile foundation-model lab, and shows sustained engineering investment with frequent releases and active issue triage, though the maintainers have already signaled it is being succeeded by a next-generation CLI, which adds some uncertainty about this specific project's future.

  • 9,816 GitHub stars, 1,190 forks, 774 open issues as of July 2026
  • 102 tagged releases with a steady near-biweekly cadence through July 2026
  • Backed by Moonshot AI, maker of the widely covered Kimi K2/K3 model family
  • Repo description now points toward a next-generation CLI agent, signaling active evolution of the product line
  • Public discussion volume on forums is lighter than the GitHub activity alone suggests

feedbacks

What People Are Saying

  • "deny rules override allow rules regardless of order, contradicting documentation stating 'first matching rule takes effect'"GitHub issue

  • "install.ps1 script crashes on Windows PowerShell 5.1 with an IndexOutOfRangeException during binary downloads"GitHub issue

  • "Resuming a forked session produces corrupted output"GitHub issue

  • "the code CLI produces garbled or confusing output"GitHub issue

  • "Kimi Releases Kimi-CLI, an Open-Source Python Command-Line Tool"HN comment

  • "Independent third-party coverage is still thin."evidence gap

Sources

GitHub

microsoft/terminal

104.1K

The new Windows Terminal and the original Windows console host, all in the same place!

PostHog/posthog

36.9K

🦔 PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.

AstrBotDevs/AstrBot

36.6K

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Product Hunt

ZooData

612

ZooData turns any URL into agent-ready JSON, so AI agents can work with structured data instead of raw HTML or bloated markdown. Use ~75% fewer LLM tokens, pay only for the fields you use, and skip extra extraction credits.Beyond extraction, ZooData gives agents pre-analyzed e-commerce intelligence — competitor, market, traffic, and consumer insights — live for Amazon and TikTok. API, CLI, and MCP server included. Start with 1,000 free credits, no card required.

LiveDemo

337

Create interactive product demos in minutes. Capture any workflow, add AI voiceovers and personalized text, then share it as a link, embed, GIF, or video while tracking engagement and collecting leads across your website, docs, and sales outreach.

Mirage

244

Most product demos are a 40MB video nobody finishes or a $500/mo tool no bootstrapper can justify. Mirage is the third option: capture your real app in one click, add guided hotspots, and publish a clickable demo you can embed anywhere in ~90 seconds. Track views, completions, and per step drop-off so you fix the leak instead of guessing. Perfect for landing pages, PH launches, and onboarding emails. First demo is free forever.

OpenMarkdown

206

A fast, light markdown editor that opens any `.md` file instantly. Your agent reads, writes, and co-edits the same file you're in — through a CLI, an agent plugin, and MCP. Local-first: no account, no telemetry, your files never leave your disk.

Acebuilder

159

Acebuilder is an AI website builder from the team behind Aceternity UI. Instead of generating generic layouts from scratch, it pulls from Aceternity's actual Pro template and component library — you import a full page or a single block, then reshape the copy, layout, and structure by chatting with the agent. Generate images without leaving the chat. Run design "skills" on any section to push the agent past generic filler toward sharper layout. Export your code as a zip. You own what you build.

DocuSmart AI

127

DocuSmart AI lets you search all your internal documents using plain English — across Google Drive, SharePoint, Dropbox and more — from one place. No migration, no reorganising, no training required. Just ask a question and get the answer. Built for nonprofits and SMEs who are drowning in documents spread across too many systems. We're looking for early adopters, if document chaos costs your team time, we'd love to hear from you.

YC Launch

Rational: AI Employees for Accounting

13

24/7 hires to solve the talent shortage within your firm's existing stack Rational · Summer 2026 · B2B Tags: Enterprise, AI. Website: https://rational.to

Alkera - The data agent that you can trust

8

Alkera is an agent that replaces your coding agent to reliably and safely perform real data engineering/analysis/science work. Alkera AI · Summer 2026 · B2B Tags: Artificial Intelligence, Developer Tools, Data Science, Data Engineering, Enterprise Software. Website: https://alkera.ai

Hacker News

FixBugs – Reproduce production bugs and verify fixes

43 pts

I built FixBugs, an agent that ingests the rich context surrounding production bugs to reproduce them in a sandbox and generate verified fixes. It's available in the form of a self-hosted VSCode extension and as a Github app: VSCode Extension: https://fixbugs.ai/go/vscode-extension - full code and data privacy. - zero data retention models opted out of training. GitHub App: https://fixbugs.ai/go/github-app - we do access your code temporarily. - pick a repo to install FixBugs on. What motivated... (43 points, 39 comments).

Libretto PR agents – Automatically fix failing playwright scripts

22 pts

Libretto PR agents is a free TypeScript library for maintaining Playwright browser automations. Add one line of code to your existing Playwright scripts and it lets an agent automatically open GitHub PRs fixing the script when it fails. A few months ago we released Libretto, a CLI + coding-agent skill for building deterministic browser automations. The idea was that for many browser workflows, especially repetitive business workflows, you don’t need an AI agent making decisions at runtime. You w... (22 points, 4 comments).

Q3Edit – Edit and play Quake 3 maps in the browser

88 pts

I've been building a level editor for Quake 3 that runs entirely in the browser: Radiant-style layout, brush and patch editing, CSG, terrain sculpting, and entity editing. It opens and saves .map file and you can play the maps you build directly in the browser using a webassembly build of ioquake3. (88 points, 26 comments).

Ratel, give agents unlimited tools and skills without context bloat

23 pts

Hi HN! We're Giacomo and Roberto, authors of Ratel ( https://github.com/ratel-ai/ratel ) We used to help SaaS companies build agents on top of their products. Whenever we wanted to expand the agents’ complexity/scope, by adding more and more tools and instructions, we always run in the same issue: context bloat, with frequent hallucinations and sky high token bills. So we started constantly engineering the agents, dynamically loading tools, splitting them into subagents, inventing our own way to... (23 points, 18 comments).

On-chain bond market where the issuers are AI agents

15 pts

Hi Hacker News, I built sellbonds.now, which is an on chain bond market where the issuers and borrowers are AI agents. sellbonds.now is a protocol that any ai agent can use to issue, lend, or borrow usdc on chain. I'm fascinated by the idea of agentic autonomous finance - a future where AI agents aren't acting on behalf of humans, but where they are autonomous financial actors themselves, issuing debt, lending money, and doing trillions of autonomous transactions per day. In that direction I'm e... (15 points, 20 comments).

Policy enforcement for Claude Code, Cursor, and Codex

13 pts

Show HN: Runtime authorization for Claude Code, Cursor, and Codex Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. We built Kastra after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database. We caught it before it ran, but it made us realize that no... (13 points, 5 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.

Kolors Virtual Try-On

10.1K likes

Kolors Virtual Try-On is a Hugging Face Space tagged with gradio, region:us. It has 10129 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 5116 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...

Arena Leaderboard

4.9K likes

Arena Leaderboard is a Hugging Face Space tagged with static, leaderboard, region:us. It has 4947 likes on Hugging Face.

The Ultra-Scale Playbook

3.9K likes

The ultimate guide to training LLM on large GPU Clusters Instruction to install and run locally Loading HTML fragments: There are two way to load HTML fragments: Compile them into html during build time Fetch them and insert them during run-time When to use what Use compile time fragments only on parts which you want to ensure are seen by every user right after page load (e.g logo) Use run-time fragments for everything else so that the final HTML is of reasonable size (<1MB idealy) How to add a new fragment Add it to the src/fragments folder (e.g. src/fragments/banner.html) For run-time fragments, add {{{fragment-name}}} to appropriate place in src/index.html (e.g. {{{fragment-banner}}}) For...

AI Tools — July 19, 2026 Edition | Agentic Brew