bondTypeScript
Your coding agents, working together: configure pi, Claude Code, Codex, Copilot, opencode, Crush or Gemini once per repo, open them in Herdr and split the work across several agents, each on its own branch and worktree.
Development · Cloud · AI · Open source
I design cloud & AI architectures.
Here you'll find code, experiences and lessons learned.
$
Portfolio
Open source projects
Repositories I maintain or contribute to. Each one links to the code and its documentation.
fluzoRust
My agentic programming environment: a local-first runtime written in Rust. The MVP, in progress, will include a CLI/TUI and a coding agent with explicit permissions, budgets and cancellation.
veta-agentsPython
Agentic framework under the Veta organization: building and coordinating AI agents in Python. Under active development.
CCOInsightsPower BI
Continuous Cloud Optimization: a Power BI dashboard and guidance for continuous optimization, governance and FinOps on Azure. I maintain the project under the Azure organization.
Code →757
Starred
Projects I follow
Repos I've starred on GitHub — mostly multi-agent systems, AI tooling and infrastructure I use or that inspire me.
bradygaster/squad
AI agent teams for any project
microsoft/apm
Agent Package Manager
OpenBMB/ChatDev
LLM-powered multi-agent collaboration
Stevenic/vectra
Base de datos vectorial local para Node.js
awesome-cheap-llms
Reducción de coste en sistemas LLM
agent-openai-java-banking
Asistente bancario multi-agente en Java
Azure/aoai-apim
Escalar Azure OpenAI con APIM, PTUs y TPMs
desktop-assistant
Control de Windows con IA (Copilot SDK)
jmanuelcorral/squadcenter
Uso y monitorización de múltiples proyectos squad
Learnings
Things I'm learning
Short notes on what I'm exploring: cloud, AI, architecture and tooling.
Post · Coding agents
bond: how I got my coding agents working together
How bond came to be: my CLI for configuring pi, Claude Code, Codex, Copilot, opencode, Crush or Gemini once per repo and putting them to work as a team with Herdr and git worktrees. From my personal setup to an installable tool in twelve days.
Oct 2026
Post · Coding agents
Applying RPI strategies to my coding agents
How I built common-skills to stop repeating instructions to coding agents: from a vague idea to a reviewed change, with everyday examples and no magical autopilot.
Sep 2026
Post · Blog
EpoAura: a birthday keyboard that turned into a Linux app
A birthday gift, an AK820 Pro I could only half enjoy on Linux, and an excuse to tinker with RGB, screens and reverse engineering with AI and GPT-Astra.
Sep 2026
Experiments
Local AI lab
Tests and prototypes, mostly with models running locally: edge inference, agents, offline RAG.
Experiment · Inference
Less waiting, more agents: upgrading my local AI stack
From Lemonade and Vulkan to llama-swap, Docker and Halogen: how I upgraded my local AI stack to put agents to work. Performance, decisions and results without the alphabet soup.
Sep 2026
Experiment · Inference
Running Qwen3.8 27B locally: when the model works but the chat cuts out
How we configured Qwen3.8-27B in HalostrixLab and why updating Lemonade fixed a streaming disconnect. Local models, context and SSE explained from the ground up.
Sep 2026
Experiment · Inference
Vulkan or ROCm on Strix Halo: how I failed, measured, and chose a local inference backend
A llama.cpp experiment on AMD Strix Halo: UMA memory, failed smoke tests, reproducible gates, and a short Vulkan versus HIP/ROCm comparison.
Sep 2026