What I’m Focusing On Now#
Alright, so it’s been a minute. A quick glance at the previous version of this page reveals someone who was last coherent in early 2025 and then just… stopped updating. We’re going to fix that right now.
Professional Life#
SVP, Engineering at Lark, March 2023 - May 2025.VP Engineering at Strive Health. Joined October 2025.- Chief Tentacle Officer, Groktopus LLC. Still alive, still writing about AI and the future of work over at groktop.us.
What Changed Since I Last Updated This Page#
Look, I know the whole point of a /now page is “right now, not back then.” But given that my last update was “I really need to re-learn Python” (a sentence so 2024 it hurts), you’re getting the highlights reel.
June 19, 2026#
Shipped hugo-cyberdelic, a new Hugo theme. Spun up a standalone theme repo for the cyberdelic aesthetic I’ve been playing with: violet-black voids, neon glow, circuit-board filigree, worn analog textures. It’s still really raw. Cover image support works, the design tokens are right, but there’s a lot more to build. Filed three issues for what comes next: config-gated effects like glitch toggles and animated circuit borders, an instrument-grade reading progress bar with liquid neon fill, and ambient p5.js canvas animations. Got time to spiff it up properly.
June 18, 2026#
Published “How to Strengthen Google’s OKF With a Methodology That Converged by Design.” Google announced the Open Knowledge Format (OKF) on June 12: a vendor-neutral spec for representing knowledge as markdown files with YAML frontmatter, designed for AI agents. I’d published the Artifact Pyramid two weeks earlier, solving the same structural problem from a different angle: how to structure agent-produced research outputs for multi-agent pipelines. The convergence was immediate and independent. The piece walks through six features from the Artifact Pyramid that would enrich OKF as optional conventions: navigation hints, layer separation, inline citations, quality gates, orientation metadata, and timestamps, each filed as a proposal on Google’s OKF repo. Link here: How to Strengthen Google’s OKF With a Methodology That Converged by Design.
Filed six enhancement proposals on Google’s OKF specification repo. Issues #92 through #97 on GoogleCloudPlatform/knowledge-catalog, covering the SOURCES body section convention, mandatory layer separation, inline citations as default, quality gates between knowledge layers, agent orientation hints, and timestamp elevation. Each includes prior art from the Artifact Pyramid project and implementation guidance. Constructive engagement with an open standard that converged on the same insight independently; the best outcome is both projects getting stronger.
June 17, 2026#
Closed the Agent Resilience milestone on GroktoCrawl. Filed three issues for the agent endpoint’s silent failure modes: expired API keys producing empty stdout, SSE streams that die without a heartbeat, and prompts exceeding the 10K character limit returning invisible 422s. All three PRs landed same-day: pre-flight LLM health checks before opening SSE streams, status heartbeat events at phase boundaries, and stderr errors surfaced in stdout so tooling can actually see them. Also opened PR #267 for the next round of agent-readiness improvements.
Three SlopSearX PRs merged. Got on a roll and shipped #103 (style validation), #104 (remaining agent-readiness items), and #105 (observability) in sequence. #105 added Sentry error tracking, Prometheus Alertmanager rules, product analytics instrumentation, and a closed-loop error-to-insight pipeline. All 13 integration tests passing, all metrics zero-PII by design.
Hermes-cashew got a major agent-readiness upgrade. PR #115 landed with 17 criteria: strict mypy typing (45+ violations fixed), cyclomatic complexity gates, dead code detection via vulture, duplicate code detection, deptry for unused dependency scanning, structlog migration, log scrubbing with API key redaction, a devcontainer, runbooks, and Factory Droid CI auto-review. Agent readiness score jumped from 56% to 83%.
Open Source Projects#
I’m maintaining a few things right now:
hermes-cashew. A thought-graph memory provider for Hermes Agent. Gives AI agents persistent, structured memory across sessions instead of starting from zero every conversation. Apache 2.0, built in Python, getting real use.
groktocrawl. Self-hosted web scraping and research stack. What started as a Firecrawl alternative turned into something more capable: multi-page crawling, JS-rendered content, LLM-friendly output. Runs on Docker, works with any agent framework.
agent-skills. A growing library of reusable skill modules for Hermes Agent. Reference patterns, workflow templates, and standalone skills I’ve extracted from real use. If you’re running Hermes, there’s probably something useful in here.
hermes-council. A multi-agent debate framework that composes panels of expert personas to surface hidden assumptions and stress-test ideas. MIT licensed, open source from day one. I use it for everything from editorial review to strategic analysis.
What I’m Reading (or Rather, Listening To)#
I’m not actively reading anything at the moment, but the audiobook pipeline has been strong:
- “Different Kind of Power” by Jacinda Ardern. Recently finished. Her leadership during the Christchurch response and COVID was remarkable, and her reflection on what principled leadership looks like in practice is worth anyone’s time.
- “107 Days” by Kamala Harris. Just wrapped this up. A focused, personal account of a compressed political campaign that offers a fascinating behind-the-scenes look at how modern presidential campaigns actually operate. I wish she’d won. Hard not to think about what a different world we’d be in right now.
I should probably pick up a physical book again at some point. We’ll see.
This is my now page, inspired by Derek Sivers. It’s a snapshot of what I’m focused on at this point in my life. I promise not to let another four months go by before the next update.
More research on my about Now Pages note.