Tools Bench.

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

Last Brew Time: Aug 26, 2026, 11:34 AM PT

Insight

Builders this run are racing to hand autonomous agents the scaffolding humans used to supply by hand

01.SKILL MARKETPLACES

02.MEMORY AND OVERSIGHT LAYERS

03.SPENDING POWER

Featured

GitHub110.8K

browser-use/browser-use

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

github
Browser Use — the AI browser agent that fills forms, extracts data, and automates the web

Market Signal

Why It Has Market Pull

browser-use is a mature, widely-adopted open-source library that lets AI agents drive real browsers, backed by a funded Y Combinator company with an active commercial cloud offering — this is a proven, durable product rather than a passing trend.

  • 110,872 GitHub stars and 12,180 forks as of August 2026, with commits pushed the same day
  • Weekly-to-biweekly releases: 5 tagged versions between mid-July and mid-August 2026
  • $17M seed round (March 2025) led by Felicis Ventures with Y Combinator, Paul Graham, and SV Angel participating
  • Listed in the MIT AI Agent Index as a leading browser-automation agent framework
  • 462 watchers and 30+ recent external contributors show ongoing community engagement, not a single-maintainer project

feedbacks

What People Are Saying

  • "rapidly becoming the go-to choice for AI-enhanced browser automation"Dev.to article

  • "PDF export renders markdown as literal syntax (only headers are handled)"GitHub issue

  • "Windows Smart App Control blocks unsigned browser-use.exe launcher"GitHub issue

  • "failed automatic new-tab switch is reported as successful after click"GitHub issue

  • "Not able to login to x.com using Browser use"GitHub issue

  • "We Raised $17M to Build the Future of Web for Agents"company blog post

  • "Browser Use, the tool making it easier for AI agents to navigate websites, raises $17M"TechCrunch article

GitHub34.3K

anthropics/claude-plugins-official

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Market Signal

Why It Has Market Pull

This is Anthropic's own first-party plugin directory for Claude Code, not a third-party wrapper — it ships near-daily updates, has absorbed thousands of merged pull requests, and already lists partner integrations from companies like Unity and Carta, making it the closest thing to a canonical extension marketplace for the Claude Code ecosystem.

  • 34,300+ stars and 3,880+ forks on the official Anthropic GitHub organization
  • Over 5,590 pull requests merged as of Aug 2026, several per day, with zero maintenance gaps since the Nov 2025 launch
  • 1,018 open issues reflect an active, high-volume submission pipeline rather than neglect
  • Recent merges add named partner listings (Unity Technologies, Carta, NetSuite) within the last week
  • First-party backing from Anthropic gives it unmatched trust relative to independent plugin collections

feedbacks

What People Are Saying

  • "Plugin marked as "Published" on plugins/submissions but not available marketplace directory"GitHub issue

  • "[BUG] Slack MCP plugin fails to authenticate: Incompatible auth server"GitHub issue

  • "cannot add anthropics/claude-plugins-official"GitHub issue

  • "Anthropic does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended"official documentation

  • "Best Claude Code Plugins (2026): 11 Tested, 4 Worth Keeping"blog article

  • "GitHub repos can be added as marketplaces with no verification, and quality depends on the maintainer"blog article

HF Spaces280 likes

MiniMax Music 3 Studio

MiniMax Music 3 Studio — diffusers demo Streams full songs from lyrics + a structured caption using the MiniMaxMusic3Pipeline diffusers port. The input surface is a single Suno-inspired custom gr.HTML composer (Simple ↔ Studio modes, section-tag chips, structured-caption fields per the official prompting guide) that drives Gradio events via trigger()/props.value; styling uses only theme CSS vars so it follows the Citrus theme natively. Weights: MiniMaxAI/MiniMax-Music3 AoTI kernels: diffusers-internal-dev/MiniMax-Music3-aoti (compiled on RTX Pro 6000, matching ZeroGPU hardware) Generation streams chunk by chunk with a configurable playback headroom. The 8B language-model stage runs eager on....

Market Signal

Why It Has Market Pull

MiniMax Music 3 Studio is the official hosted demo from MiniMax, a well-funded, well-known Chinese AI company, for its newly open-weighted Music 3.0 model that generates complete five-minute songs with coherent vocals and arrangement. This is a credible, well-covered release with real engineering depth and growing developer adoption.

  • Official GitHub repo (MiniMax-AI/MiniMax-Music3) has 730 stars and 61 forks within days of release
  • Open-weights release shipped August 13-14, 2026 with weights, inference code, and three documented serving paths the same day
  • Hugging Face Space run by the verified MiniMaxAI org has 280 likes and is actively running
  • Covered by multiple independent reviews the week of release
  • Community feature requests active on the space and a genuine praise thread
  • Hands-on review found solid English vocal quality but noted weaker multilingual output — a specific, credible critique

feedbacks

What People Are Saying

  • "Great work!"HF Space discussion

  • "Provide automatic copy of completed song/video files to permanent user storage"HF Space discussion

  • "solid English vocals but weak multilingual output"Review article

  • "far off the mark compared to the actual sound of regional film music"Review article

  • "730 stars, 61 forks within days of release"GitHub

  • "sound quality is strong, though some note the songs can feel monotonous"X reply

Sources

GitHub

DietrichGebert/ponytail

112.3K

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Alishahryar1/free-claude-code

50.2K

Use Claude Code, Codex, Pi, and OpenCode for free (1.3B+ free tokens) from your terminal, app, IDE, or phone like OpenClaw (voice supported + ToS friendly)

tinyhumansai/openhuman

38.1K

Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.

MadsLorentzen/ai-job-search

36.3K

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

K-Dense-AI/scientific-agent-skills

34.7K

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 175,000+ scientists worldwide. 163 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

Product Hunt

akta.pro

415

Private company data with 4x the depth and 2x the coverage of PitchBook, plus 100+ event signals and news across companies, industries, and topics. Source and diligence deals or make outreach lists and trigger outbound. Built for financial services and GTM teams, pay-as-you-go.

Agnost AI

288

Agnost AI analyzes conversations between users and your production AI agents and discovers: silent failures, agent behavior drift, hallucinations, user frustration, hidden feature requests, and churn signals. It groups them into recurring patterns, shows the exact users and conversations behind each insight, and turns them into evals and fixes.

Jotform AI Data Assistant

241

Jotform Data Assistant turns the data you collect into answers, insights, and action. Simply ask it to create or organize tables, analyze submissions, uncover trends, generate charts, summarize responses, or update records in bulk. Built directly into Jotform Tables and Inbox, it helps you manage your entire post-submission workflow through natural conversation, no formulas, complex filters, or repetitive manual work required.

Nimbia

171

Nimbia is an AI that does screen-sharing calls to onboard and train new users of software products. It speaks, listens, and can actually click on the user's screen, so it can be truly helpful. The very first company using Nimbia is growing 40% faster because of it. When they ran an A/B test against their previous onboarding solution, Nimbia delivered 1.4X higher week-one activation and trial-to-paid conversion.

Purchase API by Agentcard

131

your agent can now buy things with one API call. tell it buy X from Y and Agentcard finds the product, runs checkout and pays with a single use card. works today with DoorDash, Amazon and most Shopify and Stripe stores. try it from agentcard.sh, your first order is free!

Altar II

129

Shockingly thin, fully mechanical. Altar II combines a superlative typing experience with an unbelievable design.

YC Launch

Hop Aero 🚀 Rocket Cargo

Hop Aero delivers an autonomous 21st century D-Day Hop Aero · Summer 2026 · Industrials Website: https://hopaero.com

Hacker News

TeXbrain, a LaTeX editor that runs pdfTeX in the browser via WASM

113 pts

I'm a master's engineering student and a big fan of LaTeX, which I used for my thesis and research articles. I have used Overleaf and that was fine until I wanted to git sync, which unfortunately sits behind a paywall. Since I didn't want to pay subscriptions for things that should simply just work, I built the editor I wanted in my free time, where you open a tab, write LaTeX, get your PDF and the files stay all in one folder on my disk. TeXbrain is a static site with no backend. pdfTeX is comp... (113 points, 27 comments).

OzBrain, a shared brain for knowledge between agents and your team

92 pts

I think agent-first chat interfaces will be a primary software modality and busy dashboard/UI will go away. I’m not sure who exactly wins it, but I want my knowledge to grow/go with me. A lot of the “knowledge” ie research, analysis, reasoning will be done by agents as the primary user. Our current notes tools & tasks management systems were built for humans… I don’t care what the 17th thing on my bug backlog is. I want to conduct agents that can execute for me and do great work. What I built Oz... (92 points, 55 comments).

Keenable – A different web search API for AI agents

11 pts

Hey HN! We built https://keenable.ai , a different web search API for AI agents. Keenable searches our own 100B+ page index. We are focused on low cost and latency (p95 <250ms from us-east). We don’t believe in benchmaxxing, so we open-sourced our internal benchmarking suite, NEEDLE (available at https://keenableai.github.io/needle ): a live benchmark that compares Keenable with other search APIs on fresh agent-like queries. I spent seven years at Amazon as a scientist working on web grounding f... (11 points, 5 comments).

Declaude

6 pts

I had to develop a course related to quantum chemistry and unfortunately, Claude just kept writing it in its own very annoying claude-speak. It actually cost our team a lot of time and tokens to wrestle it to just speak like a normal human. We used skills, as well as initial prompts and subagents to make sure that all of the tics were gone, but there was one too many times where it just wouldn't fix itself despite telling it in the prior prompt! I made speak-english based off of https://github.c... (6 points, 2 comments).

I built an open source video editor that you can control with an LLM

4 pts

Hey HN, my name is David. I'm building an open source video editor. I'm a novice at video editing and previously only used iMovie. I recently opened iMovie to edit a video but noticed it didn't have some features I wanted, like text overlays. Apple probably hasn't updated it in ages. How hard could it be to build one? It's actually pretty hard. There are so many basic things that need to get right, like behavior in the timeline, drag and drop, coloring, etc. Good thing there are LLMs. I was able... (4 points, 0 comments).

Traccia - Observability, Runtime Control & Audit for agents

4 pts

AI applications are becoming agents, which has started to take autonomous decisions. There are plenty of tools and platform available to trace, and observe what an agent or llms calls does. They are good in what they do, but tracing and observability isnt enough for AI agents era. We need a solution that can help you observe, evaluate, create run time policies to govern and finally audit the actions of the agent. We built Traccia to solve this problem. The good part, all of these can be achieved... (4 points, 0 comments).

HF Spaces

Qwen-Image-Edit-2511-LoRAs-Fast

2.7K likes

Demo of the Collection of Qwen Image Edit LoRAs Qwen-Image-Edit-2511-LoRAs-Fast is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 2671 likes on Hugging Face.

Agent Memory Leaderboard

766 likes

Unified memory evaluation · Results expected August 12. Agent Memory Leaderboard · 记忆之巅 A unified, open, and reproducible evaluation platform for long-term memory systems and memory-enabled agents. Agent Memory Leaderboard (AML) compares research methods and commercial products under one evaluation contract. Candidate systems implement memory Add and Search; the official platform fixes Answer, Eval, datasets, models, configurations, result review, and publication. > First public release: The inaugural verified leaderboard is expected to be published on August 12, 2026. > 首期发布： 首期经核验榜单预计将于 2026 年 8 月 12 日发布。 Results are separated along two independent dimensions. Textual and coding tasks use...

MiniMax H3 Turbo LoRA

291 likes

Video generation with a synchronized soundtrack MiniMax-H3 — unquantized, split across two Spaces Joint video and soundtrack out of a single denoising pass, at bfloat16 with no quantization anywhere. This Space is the denoising half: the 61.73 GiB transformer and the two autoencoders. The 62.14 GiB Qwen3-VL conditioner runs in qwen3vl-conditioner, which this Space calls over the gradio API for every request. The weights are the public MiniMaxAI/MiniMax-H3 diffusers checkpoint. MiniMax-H3 is 195.9 GiB in bfloat16 and a ZeroGPU Space is evicted at 150 GB of storage. An unquantized single Space is therefore impossible, which is why quantized demos of it run NVFP4 or float8 weights. Cut the Mini...

SenseNova-U1.5-8B-MoT

51 likes

Unified text-to-image and image editing model Text-to-image and image editing demo for sensenova/SenseNova-U1.5-8B-MoT, a natively unified multimodal model (18B params, bf16) built on the NEO-unify architecture. Leave the image upload empty for text-to-image generation, or upload one or more images and write an edit instruction for image editing. Advanced options exposes denoising steps, guidance scale, timestep shift, image guidance (editing) and the seed. The step count defaults to 28 rather than the model card's 50: a fixed-seed A/B found 28 keeps composition, prompt adherence and text rendering intact — losing only some micro-texture in landscape and skin, and nothing measurable when edi...

Wan2.2 14B Fast Preview

1.5K likes

generate a video from an image with a text prompt Wan2.2 14B Fast Preview is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 1472 likes on Hugging Face.

FLUX.2 Klein multi-LoRA

463 likes

Use multiple FLUX.2-Klein LoRAs Note: This space is experimental and may log image-uploads during certain periods for performance monitoring. Always comply with HF and model Terms of Service. Any stored images are automatically deleted after 7 days. FLUX.2 Klein multi-LoRA is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 463 likes on Hugging Face.