Lyall Paldano
CV
© 2026 Lyall Paldano. All rights reserved.
Back to Home

OpenClaw

Jan 2026 - Present

Self-hosted multi-agent autonomous coding pipeline. Five specialised LLM agents (Orchestrator, Coder, Reviewer, QA, PM) collaborate to produce tested, reviewed pull requests, all controlled from Telegram.

Tech Stack
TypeScriptBunLobster YAMLSupabasepgvectorPlaywrightaxe-coreTelegram Bot APIHetznerClaude Haiku 4.5
Repository

Challenge

Most AI coding tools run as single-agent assistants. I wanted to see what happens when you split the work across specialised agents with deterministic orchestration and a human approval gate, on a single VPS, with no cloud dependencies beyond LLM API calls.

Solution

Architected a 5-agent pipeline on Hetzner CPX32, orchestrated through Lobster YAML so prompt injection cannot derail the workflow. Built ClawRouter for USDC micropayment-based model routing across multiple LLM providers, plus a Playwright visual QA module for automated accessibility and computed-style auditing.

Outcome

385+ passing tests on the primary testbed project (KPI-Canvas). Dozens of end-to-end feature builds shipped through the pipeline. I use it as my development acceleration infrastructure.

Skills Learned

Multi-agent orchestrationDeterministic pipeline designPrompt injection mitigationLLM cost engineeringSelf-hosted AI infrastructureUSDC micropayment routing