
Onyx
The open source AI teammate you've dreamed of
Onyx launched on September 23, 2025 with 165 votes, #189 of 8,160 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
AI for real work, not just chat. Connect any LLM to your team's data. Build AI agents with actions & MCP. Search internal docs & the web. Deep research everything. All private and open source.
Onyx is the open-source AI chat connected to your docs, apps, and people. Deep research, MCP, code interpreter, web search, and other advanced chat features. Encourage collaboration with chat sharing, user feedback, and usagefrom onyx.app
Does a similar job
all alternatives →
Open-source Deep Research across workplace applications2025 · github.com · ▲125I’ve been using deep research on OpenAI and Perplexity and it’s been just amazing at gathering data across a lot of related and chained searches. Just earlier today, I asked “What are some marquee tech companies / hot startups (not including the giants like FAAMG, Samsung, Nvidia etc.)”. It’s a pretty involved question and looking up “marquee tech startups” or "hot tech startups" on Google gave me nothing useful. Deep research on both ChatGPT and Perplexity gave really high quality responses with ChatGPT siding on slightly larger scaleups and Perplexity siding more on up and coming…

ClarkJul 2026 · clarkchat.com · ▲264Hey folks, I've been building Clark solo, with the aim to match Manus agent (I really like it!) in features and capabilities, but also in its relentless ability to just complete tasks while using browser, computer etc. So far I think I've achieved 1:1 core feature parity: 1) computer use agent 2) browser use in same thread 3) wide and deep research - clark calls clark 4) integration with google tools Would love to have community feedback and for you to try it out, a couple thousand people already using it daily for very broad use cases. You can use this referral link, that hopefully works…


SokosumiMar 2026 · sokosumi.com · ▲90I'm part of the team that build Sokosumi, a marketplace where you can hire and deploy AI agents for specific tasks (research, design, sentiment analysis, etc.). Instead of one big chatbot, they’re positioning it as a directory of specialized “freelancer” agents, with a blockchain-based backend for payments and identity. Developers can also list their own agents and monetize them. Curious what people here think about this model: Will specialization make agent marketplaces more useful than general-purpose LLM tools? How viable is blockchain as the backbone for an agent economy? What pitfalls…
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art

PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, September 2025
the whole month →

The site hit #1 on HN about a year ago. Got enough traffic that I turned it into a proper API. What's there: - REST API — 35k products, manually filterable by category, free key, 60 req/min - CLI — npx anycrap random -c food - faker.js plugin — bundled, no API call, works offline - HuggingFace dataset — full 35k rows for ML/training https://anycrap.shop/developers
AI · 2025 · anycrap.shop

I made a built-from scratch Wayland Compositor to display any GUI app* in the terminal! I think there is a lot of unexplored potential in custom Wayland compositors, a lot of really cool things you can embed existing applications into! So, I started with embedding apps into the terminal because that is the easiest input/output (output is just utf-8 and I use the great `chafa` library for that, and I just read from stdin for the input). If you have any other ideas for cool Wayland compositors, let me know. I purposedly wrote 80% the app in Typescript to appeal to the most developers and…
Dev tools · 2025 · github.com
- IR
Years ago I stumbled across a basic version of this concept and it stuck with me. I knew if I was ever going to take on such a project, it would need to be flawless, but without coding experience it was just another idea that would never happen. By the end of 2024, as AI coding tools exploded everywhere, I finally had a way to make it real. I started from zero knowledge and spent months collaborating with AI agents as a learning experience. Every pixel and every function went through me. The AI translated what I asked for into code, but every decision was human. I didn't use existing OS…
AI · 2025 · mitchivin.com

