Chris Weaver

@ArtemXTech nice writeup. I'm exploring/writing a piece on FRAG (filesystem rag) where we combine bash commands with BM25 for maximum search capability. Have you given this combo any thought?

Every enterprise AI tool right now is trying to be a chatbot. This works for maybe 30% of workplace questions. Most of the time, people just need to find something. A doc, a thread, a spec. Onyx now does both in a single unified interface. One input bar, automatic intent detection, instant results for lookups and AI answers for real questions. Sub-400ms on search, sub-1s on classification, 90%+ accuracy on routing.

We created the first agentic RAG benchmark with real workplace questions and data. - 99 questions that were actually asked by us or our users. For example, “What common pains usually come up in discovery calls with prospects?” - 220k messy real documents from email, Slack, Github, Linear, Fireflies, Hubspot, and Google Drive. - 4 independent LLM judges. - ChatGPT, Claude, Notion AI, and Onyx as competitors. Onyx outperformed ChatGPT, Claude, and Notion AI by ~2:1. ChatGPT came in a distant second, followed closely by Claude, with Notion AI in the rear. We’ve published the raw results across different agents (and what we do differently to outperform) in our full blog here: onyx.app/blog/benchmark….

Craft represents your Slack, Google Drive, Notion (etc.), as a file system, and gives a coding agent the ability to run bash and python against them. Compared to RAG or MCP, this allows Craft to work well at 100k+ doc scale. Try at cloud.onyx.app/auth/signup

Introducing Craft — Cowork, but over *all* your workplace docs instead of just your desktop. Craft lets anyone perform complex ad-hoc analysis and build repeatable, always updating dashboards based on that analysis. And it’s all open source.

We matched ChatGPTs deep research, but with open weight models. In a blind head-to-head, win-rate was exactly 50%.

we built the most beautiful open-source AI chat 😎

For those interested in how it works, check out the implementation github.com/onyx-dot-app/o…

We just added MCP support to Onyx. It’s awesome

7/7 Checkout the implementation here github.com/onyx-dot-app/o… Or try for free here cloud.onyx.app

6/7 We rebuilt using this approach with Exa (adding Google PSE and Firecrawl soon). Web search is actually usable now. If you're building AI search, don't overthink it. The SOTA approach is elegantly simple.

1/7 🧵Figured out how ChatGPT does web search. Here's what OpenAI, Claude, and Perplexity are actually doing under the hood (and how we fixed our 60-second search times)

One thing teams don’t talk about enough is the importance of good docs. We put 2 weeks into revamping our docs from the ground up and immediately saw a 3x on engagement. Shoutout to @mintlify If you want to see how we did it, check it out here: docs.onyx.app

@Yuhong_S @onyx_dot_app It's beautiful 😍😍

We spoke to hundreds of users last month and their message is undeniable - so we’re taking a big bet We’re relaunching @onyx_dot_app as THE entry point to GenAI at work. As part of this big bet, we’ve revamped our website which explains it more clearly: onyx.app