I build AI platforms and agent infrastructure.

• marsClaw — Building a personal chat assistant with Bun, SQLite and MCP

  18 Aug 2026·11 min read

  Hey Guys, for the past few months I have been building a small thing called marsClaw. It is a personal assistant which lives inside a chat app…

• Why MCP, Not REST APIs?

  3 Aug 2026·10 min read

  The question comes up the moment you try to make an agent use your existing API. The answer isn't that REST is wrong — it's that REST was designed for a client who reads the docs at build time, and an LLM isn't that client.

• I Hired a Platform Engineer Who Can’t Break Anything

  29 Jul 2026·13 min read

  Onboarding an AI agent onto my cloud with 15 tools, viewer-only credentials, and no path to production

• From Raw Events to Per-User Intelligence: The Techniques Behind a Persona & Propensity System

  6 Jul 2026·12 min read

  A field guide to the techniques that turn billions of behavioural events into per-user personas and forward-looking scores — identity resolution, RFM, quantile bucketing, time-share archetyping, temporal validation, leakage control, and transparent composite scoring.

• Navigating the 2026 Agent Ecosystem: LangGraph vs. OpenClaw vs. Google Agent SDK (ADK)

  10 Jun 2026·6 min read

  Choosing the right framework for deterministic orchestration, autonomous execution, or cloud-native ecosystem scaling.

• Docker Desktop vs. Colima: Choosing the Right Container Runtime for macOS

  7 Jun 2026·4 min read

  If you’ve been developing on macOS for a while, Docker Desktop has likely been a staple in your toolchain. For years, it was the…

Things I've built

• platform-mcpRead-only MCP server exposing 15 GCP observability tools across logs, metrics, cost and asset inventory, so an LLM agent can triage incidents and find savings without ever mutating infrastructure. In production use by my team.
• bigquery-mcpMCP server for plain-language questions over BigQuery. Dry-run cost estimation, tiered confirmation, a hard per-query scan cap, and SELECT-only execution under each user’s own IAM credentials.
• LimbiqNeurotransmitter-inspired memory layer that makes any LLM appear to learn across conversations — FAISS vector search plus a knowledge graph, with no change to model weights. Published on PyPI.
• marsClawMulti-channel LLM agent across Telegram, Slack and WhatsApp on the Claude Agent SDK, with provider failover, capability-removal-by-default security, and an append-only tool audit log.
• FleetOS17-service Go platform streaming 20-DOF robot telemetry over gRPC into Kafka, with a Temporal-orchestrated ML lifecycle running from experience collection through GPU training to canary rollout with automatic rollback.
• kube-gpukubectl plugin giving real-time visibility into NVIDIA MIG partitions — per-pod GPU-slice assignment, pending job queues, and CUDA/NCCL/OOM highlighting in streamed logs. Ships via Homebrew and krew.
• KithlyConsumer product built end-to-end and solo: a React Native app, a Go API on Clean Architecture, pre-signed S3 uploads, and a Redis/asynq worker pipeline that stitches contributor clips into one finished video.
• ZylobinCivic recycling platform built solo across four codebases — React Native app, admin console, marketing site and Node API — covering 1,500+ verified collection bins across a 15-module domain.