129.0K
💫 Toolkit to help you get started with Spec-Driven Development
Tools Bench.
Product launches and open-source repos with enough signal to earn a second look.
Last Brew Time: Aug 15, 2026, 10:57 AM PT
Sources
GitHub
71.9K
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
47.2K
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
39.4K
ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀
29 editorial diagram types for Claude Code. Self-contained HTML + SVG. No shadows, no Mermaid-slop.
10.8K
The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.
Product Hunt
363
Outcome helps creators turn their content and expertise into personalized funnels that listen, understand, and deliver a useful outcome to every lead. Instead of sending everyone the same lead magnet or placing them into a predefined quiz result bucket, an Outcome Funnel uses each person’s answers together with the creator’s content, knowledge, and process to generate something made for them - an action plan, audit, score, roadmap, recommendation, and more.
283
Freebuff is a free coding agent that gives you access to the best open source models. We offer a CLI, Desktop app, Web app builder, and Cloud agent -- all free! This is the free way to build full-stack apps. No subscription, no API keys, no lock-in. Cancel your subscriptions to Claude Code, Cursor, Codex, Lovable, Replit, Bolt, Windsurf, and Devin.
Stop fixing broken scrapers. BrowserAct's AI agent builds a Bot from your plain-English description, tests it in a real browser, and keeps it running even when the site changes. Structured data lands in your CSV, JSON, API, or tools like Make, n8n, and Zapier.Build once. Run reliably. Improve continuously.
Today, we’re building on the progress of our widely used Flash series by introducing Gemini 3.7 Flash, our most intelligent workhorse model yet for coding and agents.
[Open-Source] Local Multi Agent Harness that wraps around coding agents you already pay for like Claude Code and Codex to run an office of forever running agents working for you 24/7 in "the office" styled simulation. Be the boss of this office or let your clone be the boss when you are not available. For Developers, Product Managers, Designers, Founders, Sales, Marketing, Legal, HR or anyone who works in tech.
DeepSeek Harness is an open-source agent runtime where models, tools, prompts, storage, the agent loop, and even the UI are plugins. You compose profiles and agent presets, run programmatic tool calling, and keep a full event log for recovery and replay.
YC Launch
Helping entrepreneurs build data businesses for physical AI. DeepReach Inc. · Summer 2026 · B2B Tags: Artificial Intelligence, Hardware, Machine Learning, Robotics, Computer Vision. Website: http://www.deepreach.ai
We spin up a dedicated sales agent for every single visitor to your marketplace. Palisade · Summer 2026 · B2B Tags: Artificial Intelligence, Marketplace, Sales, E-commerce. Website: https://palisade.run
AI-native Accounting Firm for Enterprise Billow AI Labs · Summer 2026 · B2B Tags: Artificial Intelligence, Finance, B2B, Workflow Automation. Website: https://thebillow.ai/
A mobile app to watch vertical anime shorts, created with AI. MOCHI.TV · Summer 2026 · Consumer Tags: Artificial Intelligence, Consumer. Website: https://www.mochi.tv/
We enable any company monetize its agents' traces! Magma · Summer 2026 · B2B Tags: Reinforcement Learning, Data Engineering, AI. Website: https://magmahq.ai
Buy tokens in advance with flexibility to resell unused capacity up to 30%+ off - or more for larger orders via direct quotes Touchmark · Summer 2026 · B2B Tags: Artificial Intelligence, Infrastructure. Website: https://touchmark.ai
Hacker News
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits betwee... (527 points, 182 comments).
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... (83 points, 13 comments).
That's a bold claim. But I genuinely feel like I might have actually solved computer use (demo: https://x.com/mdlahfir/status/2088109763783700827?s=20 ) For context, I've been building agent-desktop (Inspired by agent-browser by Vercel Labs), an automation CLI for desktop apps. It's like Playwright but for desktops, not just native, but for Chromium apps as well. Trust me, yes, Chromium apps whose accessibility tree is dense. MacOS is GA; I'm almost close to launching for Windows and Linux! So,... (6 points, 0 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... (18 points, 1 comments).
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... (8 points, 3 comments).
Artifex is a machine-first, headless CLI runtime built for autonomous coding agents to author, validate, and render media node graphs locally. The agent talks to Artifex through a structured CLI interface. Workflows are DAGs, and each node is a plugin that can implement its own execution logic.. Each node has capability to inject logic into graph processing, WebGPU rendering, audio processing and their own SKILL.md file. Nodes can also inject their react components (not available with CLI) - whi... (7 points, 0 comments).
HF Spaces
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 2551 likes on Hugging Face.
347 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...
254 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...
140 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...
108 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....
106 likes
Ultra-fast local NVFP4 video + synchronized audio generation MiniMax-H3 Ultra Fast — local conditioner + pruned NVFP4 on Blackwell Joint video and synchronized sound from MiniMax-H3, rebuilt for a single 96 GB Blackwell ZeroGPU worker. | layer | optimization | |---|---| | Weights | 12.5 GB pruned NVFP4 transformer: 20.1B effective parameters instead of 33.1B/61.7 GiB BF16. | | Compute | Native CUDA 13 NVFP4 tensor-core GEMMs through comfy-kitchen; higher-precision norms, embeddings and output heads. | | Residency | Transformer, conditioner and both VAEs remain GPU-resident during generation—no layerwise CPU offload. | | Conditioner | Local 15.7 GB Qwen3-VL NVFP4-AWQ checkpoint containing onl...