Tools Bench.

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

Last Brew Time: Oct 16, 2026, 11:55 AM PT

Insight

Builders this run are standardizing the plumbing around coding agents rather than the agents themselves

01.OFFICIAL PLUGIN AND SKILL ECOSYSTEMS

02.AGENT GOVERNANCE AND COST LAYERS

03.DISPOSABLE REMIXES OF THE SAME FOUNDATION CHECKPOINTS

Featured

GitHub40.3K

anthropics/claude-plugins-official

Official, Anthropic-managed directory of high quality Claude Code Plugins.

youtube
Claude Plugins Give You Superpowers, Here's How to Unlock Them

Market Signal

Why It Has Market Pull

This is the real, official Anthropic organization (confirmed via its GitHub org profile: blog anthropic.com, account active since 2020, 115 public repos) running the canonical plugin directory for Claude Code. It has strong, sustained press coverage, a formal submission process, and named integration partners — about as close to a verified, company-backed signal as a tool in this category can get.

  • 40,399 real GitHub stars, 4,397 forks, 246 watchers, 1,140 open issues; created November 2025 and pushed within the last day.
  • Confirmed official org: the account resolves to Anthropic (blog anthropic.com), not a third-party mirror.
  • Covered by at least five independent outlets in 2026 (Unite.AI, AIToolly, Tech Times, Dev.to, Daily.dev) tracking growth from roughly 20,000 to over 38,000 stars.
  • Named external contributors in the directory include GitHub, GitLab, Linear, Asana, Firebase, Playwright, Terraform, and Discord — concrete evidence of real ecosystem partners, not just self-reported traction.
  • A caveat worth noting: Anthropic itself has flagged unverified MCP risk in some third-party submissions.

feedbacks

What People Are Saying

  • "Anthropic Opens Directory Submission Portal for Claude Plugins"Unite.AI article

  • "the repository... has accumulated over 20,000 stars as developers seek a reliable alternative to the scattered community marketplaces that preceded it"Industry coverage

  • "Claude Code Plugins Get Official Directory: Anthropic Flags Unverified MCP Risks"Tech Times headline

  • "Anthropic's Official Plugin Directory: What Immutable Slugs and Auto-Migration Teach About Agent Tool Versioning"Dev.to article

  • "High-quality Claude Code Plugins Managed by Anthropic Official"Daily.dev post

  • "Third-party submissions must pass quality and security screening before inclusion"Industry coverage

HF Spaces66 likes

FLUX 3 Image Klein

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 66 likes on Hugging Face.

youtube
มาแล้ว! FLUX 3 Klein บน ComfyUI

Market Signal

Why It Has Market Pull

FLUX 3 Image Klein is an official open-weights release from Black Forest Labs, the lab behind the original FLUX models, launched October 15, 2026 with wide tech-press coverage. At 5.6 billion parameters it targets everyday hardware, generating a 4K image in under 9 seconds on a consumer RTX 4070, with early community reaction split between praise for editing quality and complaints about anatomical accuracy and content restrictions.

  • 68 likes on Hugging Face as of this check, up from 66 within the same day of launch
  • Built by Black Forest Labs, the official creator of the FLUX model family, not a third-party remix
  • Released October 15, 2026 and covered the same week by VentureBeat, the-decoder, and Unite.AI
  • 5.6B parameters, runs on an 8GB-VRAM consumer GPU, generates a 4K image in under 9 seconds on an RTX 4070
  • Community reaction is mixed: some call the editing 'much better than qwen,' others flag weak anatomy handling and heavy content restrictions

feedbacks

What People Are Saying

  • "FLUX 3 Image Klein is here. Open Weights with the quality of a large frontier model... 5.6B parameters and runs on a single consumer GPU."X (Black Forest Labs)

  • "it's only 5.6B and we also worked on almost all quantizations - you can run it on almost all RTX cards now... it's also the best at Editing."X reply (Black Forest Labs team member)

  • "so good, much better than qwen"X reply

  • "absolutely abysmal compared to Z-Image and Qwen... no understanding of anatomy"X reply

  • "extremely censored and prompt restrictive"X reply

  • "Open on the Bounding boxes tab"Hugging Face discussion

  • "Prompt upsampling uses the FLUX 3 Image Klein prompt upsampler's system prompts"Hugging Face discussion

Sources

GitHub

obra/superpowers

300.6K

An agentic skills framework & software development methodology that works.

debpalash/VoiceStudio

70.7K

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

HKUDS/CLI-Anything

53.4K

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

K-Dense-AI/scientific-agent-skills

51.3K

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

MadsLorentzen/ai-job-search

48.2K

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

mksglu/context-mode

30.1K

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Product Hunt

Talanoa

325

Talanoa is your first email messenger. It turns messy email threads into clean, chat-like conversations, removing quotes, signatures and clutter along the way. Turn emails into actionable todos, manage your calendar without leaving your inbox, and use private, on-device AI to search, summarize and write. Connect Gmail, Outlook, iCloud or any IMAP account in one unified inbox. Everything stays on your computer: no cloud sync, no tracking, no one reading your emails.

Navige

250

Navige uses Sufficiency Intelligence to cut AI agent costs while work runs. It sends suitable requests to smaller models, caches repeated reads and trims bulky tool results. If unsure, it keeps your chosen model. Set budgets, catch runaway loops and approve sensitive actions. See costs and savings by job, with estimates clearly labelled. Watchtower is free forever. Preview changes before switching controls on.

GLM-Legal

201

LM-Legal is Z.ai’s legal AI model, built on GLM-5.3-Flash and trained for agentic legal work like contract review, evidence analysis, and compliance research. Z.ai added legal mid-training, then reinforcement learning across tens of thousands of legal task environments. It passes 19.17% of tasks on Harvey’s Legal Agent Benchmark per Vals AI, up from 6.67% for the base model. API access is application-only beta

OpenMuse

182

OpenMuse is an open-source, self-hostable personal agent with its own browser, terminal, files, and persistent work. Ask for an outcome, watch it work, review actions, and come back to the result. Compatible with any agent harness.

Polylane Impact Analysis

114

Catch issues before they break production. Polylane reviews every pull request against your live infrastructure: its config, capacity, dependencies and telemetry. For every pull request, you get a an analysis including all the evidence telling you if the pull request is safe to merge against production. Polylane also proposes missing instrumentation on your branch and keeps watching after deployment.

withHuman

107

withHuman is an approval layer for AI agents. It intercepts your agents’ tool calls before they run. Rules approve or deny routine calls automatically, and risky ones go to the right person on your team. It works across Claude Code, Codex and agents built with LangGraph, Pydantic AI and more, through an open protocol (AAP). One set of rules for every agent your company runs. Open source, with a hosted version. Use code PRODUCTHUNT for 3 months of Scale free - valid till Friday!

YC Launch

Oway: Building the Internet of Industrials

23

Oway connects industrial systems through a common protocol, giving AI the context to coordinate the physical economy. Oway · Summer 2024 · B2B Tags: B2B, API, Infrastructure, AI, Industrial. Website: https://www.shipoway.com

TRAIL by KorrAI: AI Agents for Mining Risk

19

Deployed on 5 mine sites, for Engineers who sign high-consequence mine safety reports. KorrAI · Winter 2022 · Industrials Tags: Climate, Mining, AI. Website: https://www.korrai.com

Libra Robotics: The robot workforce for infrastructure

14

One intelligence layer, many robots. Across solar farms, data centers, and beyond. Libra Robotics · Summer 2026 · Industrials Tags: Hard Tech, Robotics, Construction, Energy, AI. Website: https://www.librabots.com/

Hacker News

Indigene – Native plants for where you stand

116 pts

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... (116 points, 42 comments).

Spotatui, a Spotify TUI/GUI without web API rate limits

91 pts

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... (91 points, 19 comments).

Ito – Build Terminal UIs in Lua

73 pts

My friend and I are huge Neovim nerds. We like to rice our terminals and our editors. We just wanted a harness that we can do the same with, rice it till our hearts' desire. So, we started looking out for harnesses. Pi was great, Pi was good. But in the end, it was JavaScript. I don't have anything against JavaScript, but Lua is more fitting, and I can just as easily base it in Rust to make it even faster. So, we started cooking, and we ended up with a design that's minimal at its core and is bu... (73 points, 14 comments).

Breadcrumb, record everything on your mac + context manager for AI

49 pts

Hi HN, I'm Justin. Breadcrumb records everything you do on your Mac (screen + meetings + AI transcripts + what you and your AI decided) and turns it into memory your AI can search. It's local and encrypted. You can also teach it rules by talking to it and it makes sure the right rules turn up in the right context. Works with Claude Code / Codex / Cursor / opencode. All of this is exposed to your AI as 30+ MCP tools (here's the definitions): https://innerloop.works/breadcrumb/mcp I started it in... (49 points, 8 comments).

Opus 5.5 made a fully featured Figma clone in 3 hours / 8 prompts

40 pts

I think a chasm has been crossed. Opus 5.5 few shotted a fully working Figma for me. In the past year I have been trying to benchmark vibe coded apps and see how good they get and this week it did it with very very little guidance from me. I basically just told it reach feature parity. Prior to this vibe coded apps would resemble the real software, this is not a resemblance it's the real thing. As a casual Figma user in the past, I can't really see a difference. And if there is one you have an L... (40 points, 44 comments).

HF Spaces

Jev Decision Index

699 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...

Viggle Turbo for Qwen-Image-2.1

322 likes

6-step Qwen-Image-2.1, T2I + editing, vs-base comparison Viggle Turbo v0.3 — 6-step Qwen-Image-2.1 A distilled Qwen-Image-2.1 that generates and edits images in 6 steps with no classifier-free guidance, about 5× faster than the 40-step base model. On most prompts it is hard to tell apart from the base model; small, dense text and complicated edits (multi-reference composition, face swaps, identity-preserving edits) can still fall short of it. v0.3 (2026-09-29): at 6 steps, less grain than v0.2.1 and a little softer on fine texture. We think 6 steps is close to its capacity: every further gain we found cost something elsewhere. The new 9-step setting runs 7 turbo steps and lets the base model...

Model Pulse

227 likes

Hugging Face model download stats, history & trends Daily download history, likes and derivative families for every model on the Hugging Face Hub, going back to July 2024. Look up any model: ?model=org/name Compare up to five models on one chart See how much of a model's reach comes from its quantizations, fine-tunes, adapters and merges Galaxy: every model built on a base model, drawn as a galaxy (?view=galaxy) Wrapped: any author's last 12 months on the Hub in six cards (?view=wrapped) Weekly rankings: most downloaded, fastest growing, new breakouts, biggest families, organizations A README badge with monthly downloads and a sparkline, updated daily Data comes from daily snapshots of cfahl...

Drama 3

65 likes

Direct Fish Audio Drama 3, streaming on ZeroGPU Write a line, choose a voice, and direct the performance. This version runs the actual Drama 3 model inside a @spaces.GPU call for each take. It needs no inference endpoint or endpoint token. The Studio and Workflow tabs use the same model backend. The Space has no app-level login, daily take allowance, or allowance banner. Hugging Face applies each visitor's ZeroGPU quota and GPU queue priority. Platform quota errors are shown on the stage. First audio may take longer when a GPU must be allocated or a fresh GPU worker must initialize. Surprise is first and selected by default. Clone uses one of the three preset voices, an uploaded clip, or the...

MiniMax H3 Turbo LoRA

1.6K 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...

Wan2.2 14B Preview

584 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 584 likes on Hugging Face.