Tools Bench.

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

Last Brew Time: Aug 18, 2026, 10:56 AM PT

Insight

The busiest builders in this run aren't training anything new; they're reskinning the same handful of open models into slicker demos

Featured

Product Hunt173

Most learning tells you what to know, but doesn’t let you practice what you’ll actually do. Scholé Scenarios changes that by bringing real-world scenarios into adaptive learning. You will practice real situations throughout your lessons: explain what you just learned to a teammate, save the sale, discuss knowledgeably with a client. Scholé is an agentic learning system to adapt the learning that comes next, so you can practice the moments that matter.

Market Signal

Why It Has Market Pull

Scholé is a funded, credible company with real enterprise customers, and its new Scenarios feature just launched to strong, engaged reception. This is worth close attention — it has institutional backing, a working product already used by large organizations, and a fresh launch that's generating substantive product discussion rather than vanity upvotes.

  • Raised $3 million led by ACE Ventures, with participation from The House Fund and FundF
  • Ranked #5 Product of the Day on Product Hunt with 173 upvotes for the Scenarios launch (August 17, 2026)
  • Co-developed AI-intensive coursework with Harvard, with learners from Bank of America, NASA, Oracle, Microsoft, and Apple using the broader platform
  • Recognized by Forbes as a top way to learn AI agents for 2026
  • Maker actively answered detailed product questions at launch (grading rubrics, manager dashboards, ~2-second scenario generation)

feedbacks

What People Are Saying

  • "explaining something back is a much better test of understanding than picking a multiple choice answer"Product Hunt comment

  • "Adapting what someone practices next based on how they handled a real scenario feels much closer to actual skill development."Product Hunt comment

  • "Is there a view that tells a team lead where their people got stronger?"Product Hunt comment

  • "Can I create scenarios and share it with other people? I mean - as a manager, I might want to use Schole for coaching my team."Product Hunt comment

  • "Congrats on the launch!"Product Hunt comment

  • "rubrics are derived per scenario, following best practices from literature in scenario-based learning"Product Hunt comment

Sources

GitHub

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.

《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

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

19.3K

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

Product Hunt

Meridian is an open-source AI work journal that runs entirely on your device. It writes your work up in plain English as the day goes, so by the end of the day you have a summary of everything you did. Meridian automatically drafts your updates for your project management tools like Jira, ready to post once you approve them. Do the work. Let the remembering take care of itself. No cloud, no account. MIT-licensed, free.

Omni is the AI engineer that takes your agents from a laptop to the cloud. Today, your best AI workflows still live in Claude on your machine - stopping when the lid closes, running for no one but you. Describe what you want, or bring what you've built, and Omni wires the tools and skills, tests on mock data, and hands you a running cloud agent: scheduled, long-running, shareable with your team. It keeps agents healthy too - improves system prompts, compares models, debugs and fixes failed runs.

Clears is an agentic execution platform for autonomous software delivery, helping R&D organizations move beyond individual AI tools to agentic execution across the entire SDLC.

Vendo is an open-source customization layer in your product that lets every customer add the features and micro-apps they need, just by describing what they want. Until now software has been rigid, and every customer had to adapt to it. Vendo makes it dynamic, so your product shapes itself around each customer, built on your own API and inside the guardrails you set.

OpenTrade is an open-source harness for Claude Code / Codex agents that provide the tools and guardrails to trade effectively via Robinhood's official MCP. Out of the box, agents can setup cron schedules, custom scripts to notify themselves, and persistent background sessions – all on your machine.

152

Agents don't care about vendors - they want the best API for the task. treg gives your agent 2,600+ tools (SEO, social, leads, ads, scraping) behind one URL and one token. Search by task, see price/request/response, pay per call at 0% markup. Open source.

YC Launch

Specialized robots coordinating as one crew to automate solar installation Libra Robotics · Summer 2026 · Industrials Tags: Artificial Intelligence, Hard Tech, Robotics, Construction, Energy. Website: https://www.librabots.com/

Computer-use agents that work cross-border transaction alert investigations end to end: collect evidence, produce an assessment, draft an RFI. Zomma · Summer 2026 · B2B Tags: Artificial Intelligence, Robotic Process Automation, Finance, B2B, Workflow Automation. Website: https://zommalabs.com

Vertically integrated magnet manufacturing for aerospace, robotics and defense. Mass Magnetics · Summer 2026 · Industrials Tags: Hard Tech, Drones, Manufacturing. Website: https://massmagnetics.com/

Hacker News

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... (35 points, 92 comments).

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 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/... (21 points, 3 comments).

Landing Page: https://www.trydoberman.dev/ The Problem: AI guardrails only protect against 89% of dangerous commands. This may seem pretty good until you think of it as a lock that lets 1 in 9 intruders in. What is Doberman: Doberman is a two layer security system wrapped around your LLM monitoring every input, output and tool call. The first layer is deterministic based on state of the art security guidelines, the second layer is dynamic, learning from your use and personal preferences. How is... (9 points, 5 comments).

Hey HN! We are building HarnessRouter, a canonical API for running Codex, Claude Code, Hermes, and other managed agent harnesses as your product backend. Before building HarnessRouter, I used to build our own agent harness for our products. I tried LangGraph, agent SDKs from different vendors, pydantic, LLM tool use / function call, and so on. It's a very heavy lifting engineering effort, and I am disappointed about the agent deliveries compared to what Codex, CC can deliver. That changed my min... (9 points, 12 comments).

You write a standard solution, just like on LeetCode, and run it through the CLI. It identifies the problem by ID or title, executes your code against local test cases, and shows the result. It currently supports around 1.4k problems and multiple languages, including Python, C++, Rust, Java, Go, TypeScript, Swift, and others. The project is still an MVP. System design, SQL, and concurrency problems are not supported yet, but support for more problem types is planned. Made in Haskell! (8 points, 4 comments).

HF Spaces

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 2610 likes on Hugging Face.

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...

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 — 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....

91 likes

Find bugs in your repository with GLM This Space is built automatically from the root Dockerfile and serves the Vite application with nginx on port 7860. Optional Space build variables: VITEAPIBASEURL — API origin; defaults to https://openvuln.vulnhunter.pro. VITEGITHUBREPOURL — source repository linked from the interface. OpenVuln is a Hugging Face Space tagged with docker, region:us. It has 91 likes on Hugging Face.

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 1234 likes on Hugging Face.