I Built local-rag

2026-08-12 09:43

I Built local-rag Former company's knowledge base went down because Google changed the NotebookLM API. The local digital worker lost connection overnight.I Built local-rag to fix it. Lightweight local RAG, no server, no API keys.Stack: CLI → Chroma PersistentClient (local SQLite, no daemon) → embeddinggemma-300m (768d, runs on low-spec hardware)Install: "Give yourself this skill: haoyiyin/local-rag"Drop docs in, search by semantic meaning. 20+ formats including scanned PDFs, images (tesseract OCR), audio (whisper). Archives auto-extracted.

xAI dropped Grok Bot. The pitch: persistent cloud VMs.

Each bot gets its own browser, filesystem, and terminal — keeps running after you kill your laptop. Cloud desktop, but for agents. Uses your own credentials to log into tools. No API setup. Chains multi-step work end to end, only pings you when it needs approval. Bundled with Cursor Ultra. $200/month. SuperGrok Heavy also gets it. Beta right now, desktop + iOS already shipping. $200/mo is insane for something I can't even test. That said, from their demos it's basically the same thing OpenClaw and Hermes Agent do. I'm just running a multimodal model on a Linux desktop. Visual tasks come back clean more often than not. Works for me.

2026-08-12

I've designed and used quite a few eval harnesses by now

. Here's what I keep coming back to: stronger models need less scaffolding. Pile on more constraints and you just throttle them. A simple circuit breaker does the job. Weaker models need the opposite — more harness to keep them on track. But that raises the real cost question: you pick a cheap model to save money, it fails more, and then you wrap it in complex harness logic anyway. Per-task cost ends up not far from just using a strong model.

2026-08-12

I stuffed an agent into an Android phone.

You've probably run into those short videos lately where an agent drives a phone around by itself. This one is called Mika, and it's a free open-source project. It's an Android app that works in the background through accessibility mode, so it can use pretty much any other app you have installed. Reply to someone on WeChat, scroll Xiaohongshu, drop something in a cart and check out. It finds the buttons by looking at the screen. There's no API to wire up, and it doesn't care what resolution your phone is. When it reaches a payment step or a captcha it stops and lets you finish. 🔗 github.com/wangzan101/Mika

2026-11-01

My product went profitable, and something in me broke.

Someone on Xiaohongshu posted a while back that she sells phone keyboard skins she made with Codex. Eight, ten yuan a pack. Over a thousand a month. I've been at mine for months. October: a few hundred copies, $1,200 gross. Platform fee 30%, tax 10%, so 60% should have landed. It came to just over a thousand dollars. I still don't know how the math pulled that off. I have an overseas bank account. Once lost $500 to a wire transfer off one. I'd still tell you to take payout through WorldFirst: less hassle, lower fees. You can also get a Hong Kong USD credit card tied to it that spends your WorldFirst balance directly. Digital card is free. Physical is $4. Mainland purchases under ¥200 skip the processing fee, and right now there's 1% cashback.

2026-11-01