Full-stack AI development
2 developers availableBring your business idea:
3 days to POC, 2 weeks to MVP
Agents do the work now.
Almost every system they touch was built for people alone. Rebuilding those layers is cheap enough now to be worth doing.
What reaches the agent decides the result.
Tests that run against real systems, recordings of real sessions, traces from production. Feed an agent those and the software it writes holds up.
The calls stay with us.
Which primitives to build, which problems are worth solving. Every call goes back into the environment, so we never make the same one twice.
How I work with people who have a business to build.
For founders and business owners
For engineering leaders
For career changers and juniors
15K
monthly users on a platform I built
30K+
leads generated for one client
€1M+
payments handled in production
50+
products shipped
2 weeks
from idea to a live MVP
Tools I build and use every day. Free and open source.
See exactly what is loaded in your coding agent's context window.
Agent skills that teach Claude Code and Codex how I work.
See every meta tag on a page, and fix the structured data that decides how you show up.
A few things I've shipped recently, with the stack behind each one.
A Telegram bot that runs coding agents on your own server from your phone. Send a message, watch the work stream back into the chat, and approve the plan with a button: no terminal, no SSH.
An open-source hiring marketplace where the ranking is the product: jobs surface the right candidates, candidates surface the right jobs, and both sides are scored by the same rules. Built as a reference for search that gets measured instead of guessed at.
One package that hands a web app's own features to the AI assistant running in the browser. Built in the open as a working reference for WebMCP, the draft browser API for AI tools.
Flexible options to meet your project needs and budget
For standard projects with flexible timelines
For time-sensitive projects with specific deadlines
Pay per deliverable, tailored specifically to your business goals
Expert guidance for AI transformation initiatives
What I'm learning about shipping software with AI, written up as I go.
Every website will soon serve two interfaces — one for humans, one for AI agents. Exploring WebMCP, MCP servers, generative UI, and the architectural shift making websites AI-accessible.
An honest comparison of Claude Code and Cursor IDE — from code editing and search to pricing and models. Plus where OpenAI Codex fits in. Based on daily use of both tools.
Complete guide to setting up Claude Code on a private VPS with Tailscale security, Tmux persistence, and Caddy HTTPS – code from anywhere, even your phone.
Tell me what you're building. The first call is free, and you leave with a plan either way.
Tools, libraries, and articles worth sharing.
Cloudflare's draft spec for publishing Agent Skills at a predictable URL — an index at /.well-known/agent-skills/ lists each skill as a single artifact with a type, a URL and a SHA-256 digest. Apache-2.0, v0.2.0, and a draft rather than a ratified IETF RFC.
Analytics for MCP servers — every tool call an agent makes lands as a normal PostHog event, so you get per-tool failure and latency, the agent's own account of what it was after, and the tools it went looking for and didn't find. Beta, behind a feature preview.
Binary delta-update engine from BYK. Publish a bsdiff+zstd patch next to each release and a self-updating binary walks the chain from the installed version to the target instead of downloading itself again. Zero runtime dependencies, MIT.
Claude Code / Codex skill that mines the last N days of Claude Code transcripts across every project on the machine into five fact tables — bash, errors, tokens, human corrections, fan-out — and returns a ranked list of fixes with the measured number behind each one.
Edit video by chatting with a coding agent — drop raw takes in a folder, get a cut, graded, subtitled final.mp4 back. The model never watches the footage; it reads a word-level transcript and a rendered timeline.
Cloudflare's internal AI productivity platform, open-sourced. Agents build "gadgets" — private per-user apps written from a prompt — and reach company systems through Gatekeepers, a capability-based permission layer.
Serverless cloud for AI and data teams — run functions, batch jobs, and GPU inference from Python or JavaScript with no infra to manage.
Open-source terminal multiplexer built for coding agents — run Claude Code, Codex, OpenCode and more from one terminal on any box, with persistent PTY sessions you can detach and reattach from any device, even a phone over SSH.
Kit Langton's opinionated agent skill for building production TypeScript apps with Effect v4 — workflows, services, layers, schemas, config, schedules, caches, streams, HTTP clients, and tests, with current APIs and production defaults.
Cloud for you and your agents — disposable per-second sandboxes, persistent Linux VPS with SSH/HTTPS, and Devbox cloud dev environments.
Contributions over the past year.
4,163
Contributions
759
PR
53
Week Streak
25
Day Streak
Does not include automated bots, issue resolvers, or software factories.