Tools Bench.

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

Last Brew Time: Aug 17, 2026, 11:27 AM PT

Insight

Builders are quietly standardizing the plumbing around agents instead of shipping flashier agents themselves

01.COORDINATION AND MEMORY INFRASTRUCTURE

02.TOOLS THAT SHRINK MODELS TO FIT WHATEVER HARDWARE YOU ALREADY OWN

03.NARROW VERTICAL AGENTS SOLD STRAIGHT INTO UNGLAMOROUS INDUSTRIES

Featured

GitHub53.9K

usestrix/strix

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

youtube
I Let Strix Attack My App... Here's What It Found

Market Signal

Why It Has Market Pull

Strix is an open-source autonomous AI pentesting agent that hit #1 on GitHub Trending and has raised real venture funding; it shows genuine builder and user momentum — including candid, critical independent reviews that prove people are actually running it rather than just starring it — making it worth a closer look among similar tools.

  • 54,000+ GitHub stars, 5,783 forks, 290 open issues, and 359 merged pull requests; repo created August 2025, so this growth happened in about a year
  • Hit #1 on GitHub Trending on July 3, 2026 with over 2,100 stars gained in a single day
  • Raised $6.7M from Vercel, Activant Capital, 1984 Ventures, Heavybit, and the a16z Scout Fund, founded by a 21-year-old solo technical founder
  • 'Show HN' launch reached 102 points with substantive technical debate, including direct comparisons to competitor Xbow and skepticism about how the agent's prompts were engineered
  • Weekly release cadence continuing through August 2026 (e.g. v1.5.3), showing sustained active development rather than a one-time viral spike

feedbacks

What People Are Saying

  • "Seems heavily vibe coded, down to the Claude-generated README and a lot of the LLM prompts themselves"HN comment

  • "This is a neat project, I don't know why you'd want to set it up with this comparison to Xbow"HN comment

  • "My blackbox run found nothing and cost seventeen dollars and a disabled API key, which taught me more about how to use the tool than a clean report would have."Independent review blog

  • "Strix is a genuinely capable, free, open-source autonomous pentester, and the category it belongs to is going to matter more every year."Independent review blog

  • "the spike was sharp enough that Anthropic automatically disabled the API key"Independent review blog

  • "It is not a replacement for an experienced human on nuanced business-logic flaws"Independent review blog

GitHub32.2K

AlexsJones/llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

github
llmfit — hundreds of models & providers, one command to find what runs on your hardware

Market Signal

Why It Has Market Pull

A genuinely fast-growing open-source developer utility that tells you which local LLMs will actually run on your hardware, with organic, sustained growth rather than a single viral spike — this is a real, actively-used project worth tracking even without a company behind it.

  • 32.2k GitHub stars and 2,000 forks, up from roughly 19-21k just weeks earlier — about 5,400 new stars gained in a single week
  • Reached #2 on GitHub Trending overall and #1 among Rust repositories, holding that momentum week-over-week rather than spiking once
  • 72 contributors and 351 commits in the past 30 days — active, serious ongoing development, not an abandoned demo
  • Detailed bug reports numbered past issue #519 (Windows, Jetson, multi-GPU, LM Studio integration) showing real day-to-day usage across diverse hardware, not just star-farming
  • Covered independently by daily.dev and multiple dev blogs as a standout tool for the local-LLM community

feedbacks

What People Are Saying

  • "One of the fastest-growing developer tools in the local AI ecosystem"Dev.to article

  • "hf installed but not found on model pull"GitHub issue

  • "Incomplete support of llama.cpp under windows"GitHub issue

  • "Integrated GPU detected instead of Discrete GPU"GitHub issue

  • "llmfit mis-evaluating model fit memory? ... models run fine on my hardware but llmfit says they shouldn't fit"GitHub issue

  • "LM Studio model download fails for HuggingFace community models"GitHub issue

  • "picked up nearly 5,400 stars this week alone, a pace that puts it among the fastest-growing repositories on GitHub right now"Dev.to article

Sources

GitHub

immich-app/immich

111.0K

High performance self-hosted photo and video management solution.

harry0703/MoneyPrinterTurbo

105.7K

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

santifer/career-ops

64.4K

Open-source AI job search: scan job portals, evaluate listings with a structured A-F rubric into a 1.0-5.0 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

mukul975/Anthropic-Cybersecurity-Skills

28.3K

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

jundot/omlx

18.9K

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Product Hunt

HarnessRouter Community Edition

355

Plug-and-play managed agent harnesses in your product: Codex, Claude Code and Hermes through one API on your infrastructure, now open sourced under Apache 2.0. Switch harnesses without rebuilding your backend. Sessions, streaming, files, artifacts, cancellation, failure recovery, all handled. Model provider keys, state, and deliveries under your control. Gateway, Runner, Console in one Docker container. Ready-to-use starter kit apps as inspiration of possibilities.

Blume

304

Ship beautiful, fast, AI-ready documentation from plain markdown. Blume gives you search, theming, SEO, and one-command deploys on Astro and Vite.

Expeditione

265

Created by a single person, Expeditione is an Interactive 3D Encyclopedia built to make learning fun and memorable. Instead of simply reading about a subject, you can enter handcrafted, explorable worlds and discover them through interaction. It runs directly in the browser, with no login, ads, or tracking, and is optimized to stay remarkably lightweight. The first three expeditions are free forever, with free educator resources for classroom use.

Chert

214

Chert is Vapi for FaceTime. Build and deploy interactive AI video agents that can answer and place FaceTime calls with just a few lines of code. Deploy agents for remote support, field service, telehealth intake, guided onboarding, or anything that's easier to show than explain. Try it live: FaceTime an agent right now and show it something.

Vidaya

247

Vidaya turns your wearable data, labs, and habits into a real Healthspan score and a personalized longevity plan. Built by founders tired of dashboards that show numbers but never tell you what to actually do next.

AirAlarm

124

AirAlarm turns your iPhone and AirPods into a gentler sleep alarm. Set a wake window, drift off with built-in sounds or your own media, and wake at the end of a 90-minute cycle. No Apple Watch, account, ads, analytics, or cloud sleep profile.

YC Launch

CarSignal: The AI Operating System for Auto Shops

15

Your shop runs on one AI platform: booking, diagnostics, quoting, parts, and payments all in a single loop. CarSignal · Summer 2026 · B2B Tags: SaaS, AI, Automotive. Website: https://www.trycarsignal.com

Moving Atoms : World Models for Robots

2

World Model Lab for Evaluating Robots. Moving Atoms · Summer 2026 · Industrials Tags: Hard Tech, Robotics, Virtual Reality, AI. Website: https://movingatoms.ai/

Hacker News

Mole – Deep research agent for your terminal

100 pts

Doing research with agents is fun until they blow way past budget, jumble the sources, and don't even give you the best possible answer, just sound confident. And if you want to run some research task on local data - you have no idea where your data ends up after the prompt consumes it. So I built this tool: a deep-research agent with an enforced budget, verified quotes, and a privacy boundary for local data. 1. Never spend more than you budgeted (measured overshoot is 0%). 2. Every claim carrie... (100 points, 14 comments).

1667, a terminal UI for writing fiction with language models

32 pts

Hi HN. I built 1667 for my own fiction work and now use it each day. This probably has a limited audience. Maybe an audience of one... Why a terminal interface for story writing? I'm a dev. I like to use terminals for a lot of stuff. Most WebUIs feel off to me. That's the only reason. One thing that bothers me about writing in existing tools is that they don't fit the way I write. The mental model of my story is a tree. I try many takes usually continue with just one, but sometimes I want to try... (32 points, 87 comments).

Mocktail – Free, open-source mock API server with a built-in dashboard

23 pts

Hi HN, I built the first version of Mocktail years ago. I recently came back to the project, and after a pretty substantial rebuild, v4 is now out. Mocktail is a free and open-source, self-hosted mock API server with a built-in dashboard and database, packaged as a single ~25 MB binary. You can run it locally or on your own infrastructure — no account or hosted service required. You can define endpoints and responses, generate realistic data per request, customize headers, status codes and laten... (23 points, 1 comments).

I shrank DeepSeek V4 Flash to 57GB and it wrote a compiler on my Mac

19 pts

I built a specialized package of DeepSeek V4 Flash 0731 (originally 284B total parameters, 13B active), preserving reasoning, tool calling and coding capabilities: https://huggingface.co/steadfastgaze/DeepSeek-V4-Flash-0731-... I let it write a minimal C compiler targeting ARM64, then test the result with Fibonacci and FizzBuzz programs, and it succeeded in less than 1 hour, with the full recording at: https://youtu.be/XiwSilmV8B0 You can run it on Silicon Macs with my engine https://github.com/... (19 points, 3 comments).

Hearth – a shared family workspace where an agent can build apps

9 pts

Hi HN — I built Hearth for my family: https://ourhearth.ai Hearth is a shared workspace for a household. We use it for plans, notes, schedules, people, and recurring family rituals, with an AI agent that can work across that context. Kind of like a shared Obsidian with an agent. The cool part is that the agent can also build apps on top of the family's notes and run them inside the same workspace. We have a calendar and a travel app, for instance, and all the apps I use to manage my company's op... (9 points, 3 comments).

HF Spaces

Agent Memory Leaderboard

534 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

193 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...

MiniMax Music 3 Studio

139 likes

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....

Qwen-Image-Edit-2511-LoRAs-Fast

2.6K 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 2595 likes on Hugging Face.

Wan2.2 14B Fast Preview

1.2K 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 1217 likes on Hugging Face.

QIE-2511 Rapid-AIO LoRAs Fast (Experimental)

339 likes

Demo of the Collection of Qwen Image Edit LoRAs QIE-2511 Rapid-AIO LoRAs Fast (Experimental) is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 339 likes on Hugging Face.