Michael Gifford-Santos

Work

Three systems I built and operate, and the things around them. Each of the first three has a page of its own, in the product’s own brand.

Built and operating

sigil

Agent-session infrastructure

A daemon that turns tmux into a supervised process manager for long-running AI agent sessions — observable, interruptible, attachable from any device over HTTPS, and auto-restoring after a host crash. Built because operating a fleet of coding agents surfaces failure modes no local harness handles: the one that matters most is an agent blocked on a permission prompt, alive and doing nothing, with nobody watching.

Go · open source (MIT) · github.com/mijkal/sigil See it →

mycellm

Distributed inference

Pool heterogeneous hardware, contribute capacity, draw on it. What runs today is a QUIC overlay with NAT-friendly reverse connections — seeders dial out and the gateway routes inference back down the live session, because hole-punching does not survive symmetric NAT. Continuous batching hits 4.29× throughput at concurrency 32 with single-stream latency unchanged.

Python · QUIC · open source (Apache-2.0) · PyPI · iOS app See it →

WunderGuide

Production voice agent

A voice-first travel concierge, live in the App Store and Google Play, launched Hawaiʻi-first — and a platform of about thirty services behind it, on k3s with blue/green deploys. A LiveKit agent grounded in live itinerary, location, travel-time and weather context under a real-time latency budget, given a wide tool surface to pull that context in. Retrieval is its own service group: OCR-and-web ingestion into Qdrant with reranking and reciprocal-rank fusion, a graph store alongside it, an MCP endpoint so other clients can use the same knowledge base, and hybrid vector + full-text search over Postgres for deals and business profiles.

Co-founder / CTO · Python / FastAPI · Postgres + pgvector · Qdrant · Valkey · k3s · React Native · React · LiveKit See it →

Also built