171.3K
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Tools Bench.
Product launches and open-source repos with enough signal to earn a second look.
Last Brew Time: Oct 21, 2026, 12:11 PM PT
Sources
GitHub
141.4K
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
131.4K
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
112.8K
The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
101.0K
Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
94.8K
A high-throughput and memory-efficient inference and serving engine for LLMs
Product Hunt
481
/dev/null started as a live stream from the JetBrains office. On Oct 15, 2026, Nuno Maduro, Brent Roose, Matthieu Napoli, and Pauline Vos built a social network for web developers from scratch in 48 hours, in the open. Sign in with GitHub, share code snippets, like, reply, etc, etc! Hundreds of you sent PRs. Laravel’s Taylor Otwell stopped by mid-stream (“Laravel forever”), and Vercel’s Guillermo Rauch called it “really well done.” Thank you for watching, sharing, and roasting us.
Give your agent superpowers. No subscriptions, no signups. With Composio Instant, your agent can search the web, find business contacts, create voiceovers, turn audio into text, and so much more. Try it free: composio.dev/instant
194
Hoistbay is a free desktop app for macOS and Windows that takes the repetitive work out of S3 and CloudFront. Set header rules once (Cache-Control, Content-Type, Content-Encoding by file pattern) and they apply on every upload. Download whole folders, clear CloudFront cache in one click, and switch AWS accounts instantly. Keys stay in your OS keychain, no backend, no telemetry. MIT licensed.
191
Harness² from Google Research is a plug-and-play recursive agent harnessing framework that lets LLM agents automatically evolve their execution harnesses (prompts, tools, memory) for open-world tasks—without ground-truth verifiers. Dual recursion: task-level Propose-Probe-Compose refinement + harnessing-level accumulation of reusable experience. Up to +11.5 points on professional benchmarks like WorkBuddy-Bench.
187
Exa 3.0 is the biggest search quality update to Exa’s search API for AI agents. It adds a larger embedding model, billions of new documents including 1.27B ecommerce listings and 211M+ local businesses, and Dynamic Highlights, which use 95% fewer tokens than full page text. A new Exa Lite tier costs $4 per 1,000 requests, and Exa Auto costs $7. Available now through the API.
Autopilot is an always-on docs agent from Mintlify. It watches your code and tools like Slack, drafts doc updates when something changes, and opens a pull request for your team to review. It learns your style from every PR you merge or close.
YC Launch
Verify that code works as fast as agents can write it. Simulithic · Fall 2026 · B2B Tags: Developer Tools, Infrastructure, AI. Website: https://simulithic.com
Continuous security verification for AI agents in regulated industries Armorer Labs · Fall 2026 · B2B Tags: Developer Tools, DevSecOps, Cybersecurity, AI. Website: https://armorerlabs.com
Taking over the daily work that keeps a plant running. horizontal. · Fall 2026 · Industrials Tags: Manufacturing, Automation, Industrial. Website: https://horizontal-tech.com
Catch your AI's wrong answers before your customers see them. Latent · Fall 2026 · B2B Tags: Fraud Detection, AI. Website: http://runlatent.ai/
Orgo gives AI agents their own cloud computers. Orgo · Fall 2026 · B2B Tags: Developer Tools, Cloud Computing, AI. Website: https://www.orgo.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,... (122 points, 97 comments).
Back when I lived in Central Florida, it took me years to learn what native plants could benefit wildlife and the local ecosystem as I slowly replaced parts of my yard to make it more resilient to drought. After moving to Seattle a few years ago, I had to start all of that from scratch. LLMs made the process a bit easier but I still had to routinely ask the same kinds of questions over and over, despite being far more familiar with native plants these days and leaning more on native plant societ... (119 points, 49 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).
Hi HN, Rouler is "rules for your routes". It allows you to steer network traffic across multiple network interfaces on Windows. For example: - Run Tailscale, Mullvad and OpenVPN official clients simultaneously. - Use Rouler to send Slack via the OpenVPN connection, Chrome + an IP range via Tailscale and a torrent client via Mullvad. Rouler is VPN agnostic, so you can "split-tunnel" with anything that sets up a windows network interface. I'm an independent developer from Australia and have been w... (25 points, 6 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, 5 comments).
Endo is a Higher-Order Harness (HOH). From the easiest concept to understand to the more complex ones, Endo gives you: * A single, simple UI to use any agent provider with your existing subscriptions, and hot-swap agents right in the middle of a session. * An orchestration layer, which I call HOH, allowing arbitrary composition of agents to achieve any workflow. A fun case I tried was asking Fable and Astra to mock a presidential debate. * An agent protocol that abstracts any agent. The key insi... (6 points, 0 comments).
HF Spaces
772 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 772 likes on Hugging Face.
763 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...
423 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 423 likes on Hugging Face.
163 likes
5.6B open weights. Text-to-image, editing, bounding boxes FLUX 3 Image Klein is a Hugging Face Space tagged with gradio, mcp-server, region:us. It has 163 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...
134 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. Turbo mode (optional checkbox) applies the larryvrh distillation LoRA at generation time, reducing inference from 25 steps to 7 for ~4× faster generation with minimal quality loss. MiniMax-H3 is 195.9 GiB in bfloat16 a...