Skip to content
View kenichigman's full-sized avatar
🫥
Focusing
🫥
Focusing

Block or report kenichigman

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kenichigman/README.md

I build agent systems and the homelab they run on.

Cybersecurity student. I care about protection: of people, of agents, and of the shared spaces they work in. Most of what I build runs unattended, so it has to be honest about what it did and why.

The lab — a small home lab built from ordinary machines, run like infrastructure: I am no expert. I hope what I build is of use to anyone, and if you have any suggestions please feel free to contact me.

  • A workstation tier that does the heavy work — local LLM inference and a small fleet of cloned VMs for parallel data collection. It wakes on demand under reference-counted leases, sleeps when nobody needs it, and yields instantly when a person sits down at it.
  • An always-on sentinel laptop: the lab's wake sender, host of a second-eyes reviewer agent, and a small local inference tier. It is the machine that is awake so the others don't have to be.
  • Tiered local inference on both machines — bigger models where the hardware allows, small ones where it doesn't — with mechanical fallbacks when a tier is down.
  • Storage discipline: free-space floors on every drive, verified backups, and bulk movement that is capped and scheduled so the lab never takes the household network down with it.

The harness — the lab exists to run an agent system, and the design rule that emerged is that commitment belongs to code, not to the model. A cloud agent head holds the judgment. A dispatcher layer (in shadow testing) routes bounded work to tools and local models: the model does language only — intake, summarization, phrasing — while routing, required checks, refusals, and verdicts are derived by code from verified findings. Every dispatch carries provenance and a gateway-issued idempotency key; gates fail closed. A separate reviewer agent grades the head's claims against the records, and an always-on local agent trained on my own corpus is in training as a lower-cost first responder.

The workloads

  • Nightwatch — an agentic framework for building calibrated, falsifiable agent systems. Rules are pre-registered as code, so the system argues through falsification, not discretion. The reference build is a prediction-market research engine: quarter-Kelly sizing, mechanical EV gates, Brier-score calibration, kill conditions on the doctrines themselves.
  • An audio-driven music-video engine: real audio features drive every frame. No procedural stand-ins.
  • A wake chain for the lab itself: lease-based wake, an activity-aware sleep decider, and a power log that records every verdict.
  • A congressional disclosure pipeline: STOCK Act filings ingested from primary sources.
  • A collectibles pipeline: inventory classification and pricing for an established resale operation, Python + SQLite + local LLMs. (A companion resale venture is currently parked.)

Stack: Python, C++, SQLite, Next.js, local inference (Ollama), VM fleets, multi-agent orchestration.

Pinned Loading

  1. planet-x-spherex planet-x-spherex Public

    Planet X and SPHEREx — RiverHacks x NASA Space Apps 2026: a SPHEREx epoch blink viewer

    JavaScript

  2. nightwatch-code nightwatch-code Public

    Nightwatch — an agentic framework for calibrated, falsifiable agent systems: compiled gates, Brier calibration, doctrine trip breakers, two-tier execution harness (wake leases + clone swarm)

    Python

  3. music-video music-video Public

    Audio-driven generative music-video engine: real-audio feature extraction to mosaic/datamosh/conductor rendering pipeline, with demo render

    Python

  4. stock-act-pipeline stock-act-pipeline Public

    Congressional disclosure ingestion from primary sources: House Clerk PDFs + Senate eFD, normalized, lag-measured, SQLite-backed

    Python

  5. wake-chain wake-chain Public

    Lease-based remote wake for a sleeping workstation: an always-on Linux laptop sender (originally a phone app), verified wakes, and an activity-aware sleep decider

    Kotlin