hi! i'mryana may que i'm a software engineer based in the philippines, driven by curiosity and whatever i find interesting. i learn fast with the caveat of goldfish memory (which i call my context lol) and i'm usually self-motivated that i forget to eat.
this is not like other portfolios. feel free to have a look around and explore what makes me, me.
drag cork to move. drag notes to rearrange. use +/− or pinch-wheel to zoom. click one to open.
↘ ~/may ●─●─● github @schmayterling
open github 𝕏 @schmayterling
build notes + rabbit holes
open x recruiter?
(follow the red line) → self-taught. full-stack. philippines. product work, public-service software, developer tools, infrastructure, reverse engineering, open source.
typescript + python rust + go product + systems open resume open loops agents that remember code that explains itself trajectories + evals when helpful becomes agreeable current build, open in this window. no final form. no portfolio template. this board changes when attention changes.
one giant active pile scattered screenshots dozens of windows half-finished checklists constant switching
organized by gravity, not category.
genuinely alive this website atlas weave mayspace aiproxy orchestrator weppi
this website + ai stuff. open this week.
avery / v3 the architecture is mine. memory system, subsystem model, weeks of neuroscience papers.
what keeps me going someone else is on the other end. ~/may i enjoy writing code. if ai solves every problem, what's left?_
i hate spinners. same circle. over and over.
less interested in whether it's good—
how does it work? noise shape
diffusion models
watching a photo develop. A
atlas structural code intelligence for developers and agents, with answers grounded in the repository graph.
current bench typescript sqlite mcp
W
weave an experimental memory layer for long-running agents, state tracking, and better recall.
current bench typescript agents memory
writings for discussion how WFDs work, when to write one, the states a document can be in, frontmatter format, and the markdown features available.
wfd · 2026-07-22T00:00:00+08:00 · 9 min
Atlas: structural code-intelligence for LLM agents (an empirical evaluation) 2,239-trial benchmark across 8 OSS repos: Atlas beats a text-search baseline by +0.223 deterministic, +0.127 LLM-judge, at 42% fewer tokens.
wfd · 2026-04-19T18:00:00 · 17 min
avery v3 892 commits. the personal AI agent i've been trying to build since 2023 is finally becoming something i'm proud of.
wfd · 2026-03-31T23:50:00 · 3 min
do you want me to do that? i built an AI agent with persistent memory. now i need to figure out if it's remembering the truth or just what i wanted to hear.
wfd · 2026-03-02T09:42:00 · 4 min
the usage of ai in daily work AI makes me faster. It also might be making me dumber. I'm figuring out where the line is.
wfd · 2026-02-28T02:01:00 · 3 min
giving an ai agent a hippocampus i watched a kdrama about a girl who forgets everything every morning and realized my AI agent has the same condition. so i built it a brain.
wfd · 2026-02-28T02:01:00 · 14 min
github.com remark from writings for discussion ryanaque.com a link from writings for discussion avery saying she's wound up avery v3 avery proactively writing a business guide avery v3 x.com follow me on X from avery v3 arxiv.org guarantees from do you want me to do that? github.com Mem0 from giving an ai agent a hippocampus ncbi.nlm.nih.gov The Cognitive Neuroscience of Human Memory Since H.M. from giving an ai agent a hippocampus arxiv.org AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents from giving an ai agent a hippocampus