Skip to content
View askalf's full-sized avatar

Block or report askalf

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
askalf/README.md

Own Your Stack

Own Your Stack

Own your AI infrastructure instead of renting it by the token. One subscription. Your box. Your terms.

You were sold a meter — intelligence rented by the token, your data through someone else's pipes, your tools on someone else's roadmap and someone else's pricing meeting. I'm building the opposite: a stack you actually own. The open tools are the door; a real autonomous studio running in production is the proof — the unfinished parts included.

The stack

dario own your routing — your Claude subscription in any tool (Cursor, Cline, Aider, the Agent SDK), at subscription pricing, not per-token bills npm
deepdive own your research — a local agent that plans, searches, reads, and synthesizes a cited answer, through your own router npm
hands own your computer-use — your LLM on your own mouse, keyboard, and screen, with an audit log of everything it does npm
agent own your fleet — connect any device, run the shell or Claude Code tasks the fleet dispatches npm
browser-bridge own your browser — stealth headless Chromium in a container, CDP on your own endpoint ghcr
claude-sync own your sessions — move Claude Code sessions across machines, byte-identical npm
askalf own your operation — the self-hosted AI workforce platform the whole stack runs early access

More of the stack → sprayberrylabs.com/own-your-stack

Building it in the open

It's hard, and it's not finished — that's the point. The value isn't a demo; it's the scars from running agents in production for real. I write down what actually happens.

I'm Thomas Sprayberry — 20 years of engineering, from solo founders to Fortune 500. I run Sprayberry Labs, a studio of one that moves at a team's pace because the workforce above does the heavy lifting while I architect, review, and own everything that ships.


Own Your Stack · sprayberrylabs.com · @ask_alf · hello@sprayberrylabs.com

Pinned Loading

  1. dario dario Public

    Your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, Agent SDK — at subscription pricing, not per-token bills. One local endpoint that replays Claude Code's wire shape so your traff…

    JavaScript 273 43

  2. pgflex pgflex Public

    One Postgres API. Two modes. Real PostgreSQL (pg) for production, PGlite (in-process WASM) for standalone / dev. Same SQL, same query shape, drop the server when you don't need it.

    TypeScript 1

  3. browser-bridge browser-bridge Public

    Stealth headless Chromium in a container. Exposes Chrome DevTools Protocol on 9222. Connect from Playwright, Puppeteer, MCP browser tools, or any agent that wants a remote browser without bundling …

    JavaScript 1

  4. redisflex redisflex Public

    One Redis API. Two modes. ioredis for production, in-process Map+EventEmitter for standalone / dev. Also ships a BullMQ-shaped in-memory queue so you can drop the Redis dep entirely when you don't …

    TypeScript 1

  5. hands hands Public

    Cross-platform computer-use agent. Your LLM on your mouse, keyboard, and screen. Windows (PowerShell), macOS (open + osascript), Linux (xdotool / ydotool). Voice optional, safety guardrails. Routes…

    TypeScript 1 1

  6. deepdive deepdive Public

    Local research agent. One command, cited answer. Plan → search → headless browser fetch → extract → synthesize. Every LLM call goes through your own router (dario / Anthropic-compat). Zero hosted d…

    JavaScript 2 2