306.2K
An agentic skills framework & software development methodology that works.
Tools Bench.
Product launches and open-source repos with enough signal to earn a second look.
Last Brew Time: Oct 27, 2026, 10:57 AM PT
Sources
GitHub
290.6K
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
90.2K
The design language that makes your AI harness better at design.
45.5K
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/ .
39.1K
📨 The ultimate agentic social media scheduling tool 🤖
38.5K
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
Product Hunt
Strawberry is an AI browser that can do hours of work in minutes. Strawberry's agents, which we call "Companions", can research hundreds of leads in parallel, transcribe your meetings, automate follow-ups, and handle all the repetitive admin your team keeps procrastinating. Create or hire a pre-made companion, teach it your preferences and share it with your whole team. Hundreds of teams, including Lovable, Tandem Health and ElevenLabs, already use Strawberry.
256
Most AI image tools stop at one-shot generation. SurgePix keeps going: edit any layer, swap text, repaint a region, and stay on-brand with your brand kit. Or skip the UI — open-source agent skills let Claude Code & Cursor generate and edit visuals for you.
MiniMax M3.1 Flash is MiniMax’s new Flash model for agentic tasks, coding, computer use and cybersecurity. MiniMax says it is about 3x faster online and 70% cheaper for agentic tasks than its predecessor, with output at 200+ tokens per second. Pricing is $0.15 input and $0.60 output per 1M tokens. It’s on the MiniMax API, M Plan and MiniMax Code, and weights are promised later.
186
N8N Chat UI is a no-code builder for branded AI chat widgets, built for n8n users, agencies, SaaS teams, and businesses. Design a mobile-friendly chat experience with live preview, then connect it to any n8n workflow and embed it anywhere. Unlike default n8n chat, it adds deep customization, streaming, voice and file uploads, flexible layouts, and a JavaScript API for advanced integrations.
Find issues that can make your PDFs difficult for people with disabilities to read or use, including missing image descriptions and problems with headings. See affected content highlighted on the page, review issues by severity, and get instructions on how to fix them. The checker also flags what needs human review. Upload PDFs up to 50 MB or paste a public link. Completely free, with no sign-up, no email required, and no files stored. Checks against WCAG 2.1 AA and PDF/UA.
152
2G is a sampler that looks and sounds like an early-2000s handheld devices. We imagined what Neural Synthesis would have been like back then. Describe a sound and 2G makes it. Then edit it and play it from your computer keyboard, or load your own audio instead. 2G is free for Windows and macOS, as a plugin or a standalone app, and starts you with 20 credits for generating sounds. Studio ($10/month, 7-day trial) gives you 200 credits a month.
YC Launch
Critical equipment, without the multi-year wait. Applied Kinetics · Fall 2026 · Industrials Tags: B2B, Manufacturing, Energy, AI, Industrial. Website: https://appliedkinetics.ai
On-device AI that understands your life overnight, takes on tasks with its own cursor, and drafts replies in your voice in two taps. Sentient OS · Fall 2026 · B2B Tags: Productivity, AI. Website: https://sentient-os.ai
Hacker News
Hello HN! Wonderhop is a small browser game with no account needed to play, everyday there are 4 rounds of 7 quesitons like "Name a food that a lot of people hate" The goal depends on the mode: Either gives the answer most people would give, the one no one would give, the oldest answer or the most recent one and there's a leaderboard for the day. The most interesting part of the project was understanding answers that are typed freely and in 10 languages, there was some typos, plurals, nickname,... (124 points, 97 comments).
About 11 months ago i revived the amazing but unfortunately unmaintained spotify-tui. Since then I have been working on it almost non stop, finding a lot of problems on the way. One of the main issues I ran into were the Spotify web API rate limits. Third party clients like spotatui are dependent on a developer app made in the Spotify developer dashboard, which get rate limited a lot and Spotify has slowly been deprecating endpoints from it. The workaround for this used to be using a shared clie... (92 points, 19 comments).
Hacker News discussion (15 points, 4 comments).
I've used LLMs to decompile Civ 1 and put the reconstructed C source on GitHub, along with a technical book and story. The reconstructed source builds with what i'm pretty sure is the original Microsoft C compiler and toolchain. It produces a byte-for-byte match with the original executable, aside from a four-byte correction for what appears to be a patch applied after linking. So it should be pretty close to how the original game was made; although it can't be said that this is the "original so... (10 points, 6 comments).
Hey HN, we recently open sourced our Consumer Agent Testing Tool to help teams iterate against proprietary assistants like Muse and Instinct. We built this to reduce our own frustrations with building an MCP/API for these agents to consume. The problem: testing against these tools is hard! Agent memory + account statefulness make reproducibility, in the ways required for repeatable/reliable outcomes, between agents and the APIs/MCPs they interact with very challenging. The solution: CATT lets de... (9 points, 2 comments).
Hi HN, I'm Richard, founder of Native. I'm working on open-source context ownership, to stop AI centralisation: https://github.com/withnative/native My first focus has been making Markdown vaults powerful enough so that teams can self-host all of their context (messaging, docs and projects), without it being externally fragmented or rate-limited. I'm sharing some early results: Markdown vaults can be 40× more efficient with SQLite! https://www.withnative.ai/research-and-posts/markdown-contex...... (6 points, 0 comments).
HF Spaces
1.0K likes
generate a video from an image with a text prompt Wan2.2 14B Preview is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 1026 likes on Hugging Face.
826 likes
Benchmarks and news on various repros of TypeSafe's Jev Who is rebuilding TypeSafe's Jev (System One / RLCD) in the open? This static Space opens on the Decision Index leaderboard; the News tab tracks the artifacts in one combined grid, color-coded by kind: Decoding: parallel constrained decoding on stock models (inference technique, no new weights) Diffusion: text diffusion models run in a "Jev mode" Trained: Jev-like scoring heads and fine-tunes, weights often on the Hub, promised models listed last Prior art: "this already exists" claims Explainers: architecture speculation, explainers, benchmarks and roundups Cards sort by a trending score: ♥ likes on X + 5 × GitHub stars + 8 × Hub likes...
738 likes
Real trained RL policies for the Microduck robot, running fully in the browser: MuJoCo compiled to WebAssembly steps the physics, onnxruntime-web runs the policy network at 50 Hz. No server, no backend. Two locomotion variants of the same robot are included: legs (walking, the default) and rollers (the wheeled skating variant). Press M (or hold D-pad up ~1 s on a gamepad) to switch; the roller model, meshes and policies are lazy-loaded on the first switch. | Mode | Checkpoint | What it does | |--------|-----------|--------------| | Run (legs) | BESTalphawalking.onnx | Velocity-tracking locomotion (arrows / WASD to steer) | | Sit | BESTalphasitstand.onnx | Sits down on its hull, stands back u...
564 likes
Head swap with the BFS LoRA on Qwen-Image-2.1 (+turbo) Head/face swap demo for the BFS bfsheadv1qwen2.1 LoRA on Qwen-Image-2.1, with an optional Viggle turbo 6-step mode. Example inputs are cropped from the example images in the BFS model repository (MIT license). Qwen-Image-2.1 and the Viggle turbo LoRA are under the Qwen Research License (non-commercial). Do not use or share results involving people who have not given consent. BFS Best Face Swap is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 564 likes on Hugging Face.
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...
250 likes
Uncensored Qwen-Image-2.1 generate + edit Qwen-Image-2.1 Uncensored (ZeroGPU) Demo of abenzerps/Qwen-Image-2.1-Uncensored-GGUF on Hugging Face Spaces. The repo’s GGUF files are for ComfyUI (Unet Loader (GGUF) + leejet/ComfyUI-GGUF). Spaces ZeroGPU runs PyTorch / Diffusers, so this app: Loads the official Diffusers weights Qwen/Qwen-Image-2.1 Applies qwen-image-2.1-uncensored-lora.safetensors from the same repo No safety checker. Adult / NSFW prompts are allowed. You must be 18+. For local GGUF (Q4KM recommended) use ComfyUI as described on the model card. Base: Qwen/Qwen-Image-2.1 Quant / LoRA: abenzerps/Qwen-Image-2.1-Uncensored-GGUF License: Qwen Research Qwen Image 2.1 Uncensored is a Hug...