310.1K
Skills for Real Engineers. Straight from my .agents directory.
Tools Bench.
Product launches and open-source repos with enough signal to earn a second look.
Last Brew Time: Nov 2, 2026, 11:38 AM PT
Sources
GitHub
110.5K
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
110.3K
The open-source app everyone uses to manage agents at work
92.6K
🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
59.8K
The best ChatGPT that $100 can buy.
46.4K
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Product Hunt
The screen recorder for Mac that handles the hard parts: zooms, motion, sound, and framing. Every demo and tutorial comes out polished. What's new in 4.0: - Glass Loupe, a zoom that magnifies one detail - Split screen, also for vertical video - Edit your video like you edit text - Camera cutout: you, without your background - Hide sensitive data and faces automatically - Sharper zooms, ProRes, up to 4x faster exports, and more
Research, fully automated. ClawsGO Science takes a question to discovery and writes it up as a cited paper. Its cloud lab has 500+ tools and 90+ datasets. Its long-horizon harness runs clusters of Claude and GPT agents for days. The next paradigm for science.
Riverside Agents is a team of AI agents built only for video. A Producer preps your session, an Editor turns raw recordings into a finished episode, a Clipper cuts the best moments into social clips, and a Marketer writes captions and schedules posts. You choose how much to automate, and nothing is published until you approve it. Included in every Riverside plan, with a 14-day free trial.
170
Build multichannel AI chat and voice agents for your website, Telegram, and beyond. Create specialized sub-agents to orchestrate workflows across your knowledge bases, datastores, and hundreds of third-party tools in real time. Automatically evaluate every interaction, score lead quality, and extract structured data straight from conversation transcripts.
The upgraded Precise Edit supports a context window, so it edits images at any resolution up to 8K at their original pixels and renders small text, logos, and fine detail more sharply.
140
Agentmash is an open-source multiplayer AI for teams' coding agents, a shared context layer that tells every agent which files a teammate's agent is changing, so the agents talk to each other and work on their own without overwriting anyone's code. You can switch between tasks running on different models, @mention a teammate, your own agent or a teammate's agent like in Slack, and keep skills, chats and automations in sync. Connect Claude Code, Codex, Antigravity or your own open-source models
YC Launch
Cloud VMs for running complex environments across many agent sessions Superserve · Fall 2026 · B2B Tags: Cloud Computing, Infrastructure, AI. Website: https://superserve.ai
Letterpress-1 re-imagines every aspect of developer tooling for engineering growth. The Letter Company · Fall 2026 · B2B Tags: Developer Tools, SaaS, Web Development. Website: https://letter.dev
Data and models of the distribution grid Ryhla · Fall 2026 · Industrials Tags: Solar Power, Climate, Energy, Renewable Energy, Infrastructure. Website: https://ryhla.ai
Rewbi deploys 1-10MW distributed data centers in existing industrial buildings with surplus power, which is 10+ times faster than standard data center deployment. Rewbi · Summer 2024 · Industrials Tags: B2B, Energy, Renewable Energy, Cloud Computing, ClimateTech. Website: https://www.rewbi.com/
A relay that lets copiers, scanners and business apps keep sending email through your own Microsoft 365 mailbox. Augment Inc. · Summer 2024 · B2B Website: https://augmentinc.co
Run your entire system under millions of simulated production scenarios and verify it never fails. Workers IO · Fall 2026 · B2B Tags: Developer Tools, B2B, Infrastructure, AI. Website: https://workers.io
Hacker News
I have been researching what the ultimate diff tool would look like, based on actual diffs in open source repositories. OmniDiff can diff: code (25 languages), config, images, PDFs, archives, cursors, fonts... It's fast. It can diff C++ files of tens of thousands of lines in under 100ms, on a 2023 ThinkPad T14s. It's open source. AGPLv3. It's based on real diffs. I looked at the 7400 repositories that are listed in Gentoo packages, sampled 2000 diffs and solved them manually to get a good unders... (301 points, 94 comments).
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, 98 comments).
Explore central Warsaw in voxels - slightly inspired by Minecraft, and MagicaVoxel. You can change the date, time of day and weather, explore the city, or click on a pedestrian to control them (here a bit of inspiration from Dungeon Keeper). Works best on desktop, but I tried to make it usable on mobile too. The initial load can take a while. It's based on several open datasets, including: - OpenStreetMap ( https://www.openstreetmap.org/#map=6/52.02/19.14 ) - buildings, streets, sidewalks, tram... (117 points, 22 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).
I made this a couple of months ago. Extractions were done with Gemma 4 26B MoE running on pairs of NVLinked 3090 cards with vLLM, in my basement. Seasoned with a Claude vibe-coded frontend. The travel opinions on a map are pretty neat: https://www.trustmebro.reviews/c/travel?view=map If someone wants to take it over, you can mail me. (9 points, 0 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).
HF Spaces
1.2K 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 1202 likes on Hugging Face.
858 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...
701 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 701 likes on Hugging Face.
350 likes
Semantic search for 3D assets: USD + RTX simulation previews SimReady Central USD Search — single-container demo (OpenSearch + Neo4j + Redis + deepsearch-api + asset-graph-service, SigLIP2 embeddings via a local siglip2-triton process — see docker/Dockerfile.hf-space-gpu). Runs on a GPU hardware tier (rtx-pro-6000), unlike the free-tier docker/Dockerfile.hf-space variant, which routes SigLIP2 to NVCF instead. The index itself is pulled from the artifact S3 bucket at container startup, not baked in. Deployed by github.com/NVIDIA-dev/simready-central-indexing-internal's python -m pipeline.run_pipeline deploy-space-gpu. Third-party notices: THIRDPARTYNOTICE.md. SimReady Central is a Hugging Fac...
268 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...
201 likes
Fibo 2.0 Edit Turbo image editing in 4 steps Fibo 2.0 Edit Turbo on ZeroGPU: instruction-based image editing in 4 guidance-free steps, with up to 4 reference images and an optional mask. The JSON instructions come from the Bria API's /v2/vgl/edit, written with Fibo 2.0's VGL prompts. / — Studio (replaces the classic form UI): a bespoke Photoshop-style editor (gr.Server API + custom UI): brush-to-mask, layers (source / mask / up to 3 extra references), before/after split view, run history with one-click restore, bundled example edits. All classic functionality is kept: 4 references, mask, JSON instruction override (auto-filled by the VGL writer, cleared when inputs change), seed/steps. Edits...