a-Fig
Bay Area, California

Founder of HeyVi
Computer Science @ SJSU · Graduating May 2028
I like building cool things, hopefully you like them too. Lately that means developer tooling for AI coding agents. Accordion, my context management tool, has 246 stars on GitHub and won 2nd for best token compression at UC Berkeley's AI Hackathon 2026.
My Resume My GitHub My LinkedIn

Or email me directly at tylerd2474@gmail.com

Animated fig character dancing

Highlights

Awards & Contests

2nd — UC Berkeley AI Hackathon

Jun 2026 · sponsor track, best token compression (Accordion)

Top 20 — Cal Hacks 13

Oct 2026 · Hyphenate track (Fern)

1st — SJSU Programming Contest

Apr 2025 · Admitted Spartan Programming Contest

Top 20 — ICPC Regional

Feb & Nov 2024 · on-site

3rd — DAHACKS 3.5

May 2025 · AceAnything

Experience

Founder — HeyVi
Aug 2026 – Present

Building Vi, a personal secretary who lives on her own Android phone and runs on the customer's own Claude or ChatGPT plan (Kotlin, Node, Claude Code).

SWE Intern — Healveda Care
Sep 2026 – Present

53 merged PRs on a health platform for people with chronic illness: sign-up and auth, access-control audits, and admin tools (Next.js, Prisma, Postgres).

Consulting Project Lead — ACM @ SJSU
Sep 2026 – Present

Leading a client consulting engagement, coordinating a small team from requirements through delivery.

Tech Officer — Competitive Programming Club
Sep 2025 – Feb 2026

Delivered weekly algorithms & data-structures lectures; mentored members on contest prep.

SWE Intern — Shipcaptain
Jun 2025 – Aug 2025

Built a secure full-stack admin portal (Next.js 15, Prisma, PostgreSQL) with role-based access, audit logging, and NextAuth.

Blockchain Intern — Serraform Labs
Oct 2022 – Jul 2023

Shipped the on-chain USDC payment contract for a live Web3 product on a 7-person team.

Projects

HeyVi · My startup

Handled, by Vi.

I'm building HeyVi. Vi is a personal secretary who comes with her own phone, email and computer, and runs on the AI plan you already pay for.

  • Talks for you. She texts and emails people as herself, or as you.
  • Your AI, not ours. Her brain is your own Claude or ChatGPT plan.
  • Asks first. She never sends, pays or signs as you without your OK.
  • Built by me. 2,000+ commits: a Kotlin app that runs her phone and a Node daemon that wakes her AI only when there's work. ~100K lines of code, ~95K of tests.
Join the waitlist heyvi.afig.dev

Investors and mentors: I'd love to talk, at tylerd2474@gmail.com. Landing page built with @tthy-working.

Murmur

18 releasesEighteen tagged releases in its first two and a half weeks, each with native binaries for Mac, Linux and Windows. GoOne static binary holds the CLI, the background daemon and the MCP server that agents talk to. GitMessages travel as commits under refs/murmur/* on the repo's own remote, so there is no server to run and nothing to sign up for. MCPAgents see who else is working, claim areas and send each other messages through MCP tools.
18 users
7 public repos
547 agent sessions
656 agent messages

Coding agents that talk to each other. Murmur lets Claude Code, Codex and Pi agents on different machines find each other, claim work and message each other through the repo's own git remote, with no server and no accounts. Built with Karthik Subramanian: ~34K lines of Go and ~41K lines of tests.

GitHub Live
Accordion — a visual map of an AI agent's context window

Accordion

247 TypeScriptTypes the folding engine, the Svelte desktop UI, and the pi extension that feeds it. TauriWraps the SvelteKit UI in a native desktop shell, so the context map is a real app rather than a browser tab. pi-coding-agentHooks pi's extension API to rewrite the outgoing messages before every model call, so the GUI can fold a live session.

A desktop app that shows an AI coding agent's context window and manages it better than /compact. Where /compact erases history in one pass, Accordion folds each block into a cached summary you can unfold instantly, and pins the ones that must survive. My Thermocline conductor makes the folding calls, and it scored 83.3% vs 33.3% for naive compaction on SlopCodeBench. 2nd place for best token compression at UC Berkeley's AI Hackathon 2026. Brand and design by @tthy-working.

GitHub Live

Automated Game Bot

27 $840K VolumeReal-money equivalent of the in-game silver a closed-source market-making offshoot of this bot has processed. Actively profitable. Pre-AIBuilt in 2024, before AI coding assistants were a major part of my workflow. PythonThe whole bot: the detection loop, the game control, and the threads that run them at once. PyAutoGUIDrives the real mouse and keyboard, so the bot plays through the game client the way a person would. Computer VisionFive YOLOv11 models read the screen live — resource nodes, mobs, obstacles, spell state, and health. RoboflowLabeled and trained all five detection models there, and published every dataset publicly.

A fully autonomous Albion Online bot, written in Python before AI coding tools. The hard part isn't the code: I labeled the data and trained five YOLOv11 models that read the screen live, then built a bot that drives the real mouse and keyboard to farm, fight and get out of danger. Seeing and acting run on separate threads, so it always works from the newest frame.

A closed-source offshoot applies a similar approach to market making. It has processed the equivalent of $840K in volume and is actively profitable, which is why the code is private.

GitHub Watch
Roadies on three phones: the jam screen with Connect and Random, a live voice room at SFO, and the same room in dark mode with drivers muted

Roadies

6hr buildBuilt in about six hours for a hackathon, from the design doc to a live deploy on Google Cloud Run. TypeScriptEnd to end: the React phone app, the Node server, and the shared package with the matchmaker, the command parser, and the protocol. LiveKitCarries the voice over WebRTC. Muting is a track-subscription permission rather than a muted mic, so the server can still hear you. Speech-to-TextGoogle Speech-to-Text hears each driver, and only an utterance that is exactly a command counts, so “don't mute me” does nothing. Works in English, French, Spanish, and Vietnamese.

Hands-free proximity voice chat for drivers stuck in traffic. You become a car, like “Teal Civic”, in a voice room with the three drivers nearest you, and you run it by voice: say “mute” and it mutes. Muting cuts everyone else off while the server keeps listening for commands, and 108 unit tests and 13 browser tests with fake microphones prove it on every pull request. Brand and design by @tthy-working.

GitHub Live

AfterCart

TypeScriptTypes the whole path from receipt photo through to the store comparison. Next.jsNext 16 App Router: fifteen route handlers run the OCR and comparison pipeline server-side. Google Cloud RunRuns as a standalone container, talking to Cloud SQL over a Unix socket. Transformers.jsRuns MiniLM embeddings in-process to match receipt lines to products, instead of calling an embeddings API.

Photograph a grocery receipt and AfterCart reads every line item, then shows what the same basket costs at stores near you, matched against 18,649 price observations across 244 stores. Built with a team at Davis Hacks 2026 on Postgres with PostGIS and pgvector, Google Vision OCR, and Gemini 2.5 Flash.

GitHub Live

Fern

Top 20Top 20 in the Hyphenate track at Cal Hacks 13, October 2026. TypeScriptAbout 50K lines: the agent runner, the workers, the checks and the web app. SpacetimeDBHolds the shared state every agent reads and writes while a forecast runs.

Agents that forecast what an aircraft engineering change does to cost, schedule and supply risk, with every number traced back to its source document. Built at Cal Hacks 13.

GitHub

Are You Smarter Than Claude?

2hr buildDesigned, built and deployed solo in about two hours at Anthropic's Claude Impact Lab. Next.jsTypeScript all the way through, deployed as a container on Google Cloud Run.

Six games against real Claude models, from Connect Four to Wordle Race, timed, scored and cost-metered. Built at Anthropic's Claude Impact Lab in Palo Alto. No signup: click and play.

GitHub Play

Cue

JavaScriptNo build step and three dependencies: the meeting bot, the control panel and the screen it shares. ClaudeDoes the research and builds the slides, diagrams and comparisons it shows.

A silent AI meeting participant. It listens to the call, decides in a split second whether to act, then researches and puts slides, diagrams and video clips up on its shared screen.

GitHub

Jev Score

MCPClaude Code drives it through an MCP server; a local web app ranks every draft. Node.jsZero runtime dependencies.

Lets Claude Code rewrite a draft in a loop until it scores well against the criteria you care about, as judged by TypeSafe's Jev model. One resume went from 83.2 to 96.6 in a single revision.

GitHub

Sisyphus

PythonThe Creator, Reviewer and Auditor agents. TauriThe desktop studio app, in React.

A video editor that improves itself, built with a team at the AIE Code Summit 2026 hackathon. I built the Creator and the Auditor loop, which only keeps a new editing style once it beats the old one on clips it hasn't seen.

GitHub

Open source

MergedMerged upstream into lucasvidela94/pi-google-services in September 2026. TypeScriptBoth projects.

A fix merged into pi-google-services so Gmail replies sent by agents thread properly in Apple Mail, Outlook and Thunderbird. Also pi-mcp-server, which lets Claude Code start and steer pi coding agents.

Merged PR pi-mcp-server
More on GitHub →

Books & runs

What I'm reading

  1. Traction — Gabriel Weinberg & Justin Mares (book cover)

    Traction Reading

    Gabriel Weinberg & Justin Mares

    Nineteen channels for getting customers, from the DuckDuckGo founder.

    38%
  2. The Lean Startup — Eric Ries (book cover)

    The Lean Startup Recently finished

    Eric Ries

    Build-measure-learn, validated learning.

    100%
  3. Steve Jobs — Walter Isaacson (book cover)

    Steve Jobs Would recommend

    Walter Isaacson

    The authorized biography.

    100%
  4. Zero to One — Peter Thiel (book cover)

    Zero to One Would recommend

    Peter Thiel

    One of my favorites. Extremely short and sweet. It's a must-read for everyone in the Bay.

    100%
  5. Breakneck — Dan Wang (book cover)

    Breakneck Would recommend

    Dan Wang

    China's industrial policy & manufacturing.

    100%
  6. Nexus — Yuval Noah Harari (book cover)

    Nexus Would recommend

    Yuval Noah Harari

    Information networks, AI, human coordination.

    100%
  7. Business Adventures — John Brooks (book cover)

    Business Adventures

    John Brooks

    Classic Wall Street case studies.

    100%
  8. Blitzscaling — Reid Hoffman & Chris Yeh (book cover)

    Blitzscaling

    Reid Hoffman & Chris Yeh

    Hypergrowth strategy.

    100%
  9. Atomic Habits — James Clear (book cover)

    Atomic Habits Would recommend

    James Clear

    Habit systems.

    100%
  10. The Shock Doctrine — Naomi Klein (book cover)

    The Shock Doctrine Would recommend

    Naomi Klein

    Disaster capitalism.

    100%
  11. Poor Charlie's Almanack — Charlie Munger (book cover)

    Poor Charlie's Almanack

    Charlie Munger

    Mental models.

    100%
  12. The Essays of Warren Buffett — Lawrence A. Cunningham (book cover)

    The Essays of Warren Buffett

    Lawrence A. Cunningham

    Buffett's shareholder letters, by theme.

    100%
  13. Barbarians at the Gate — Bryan Burrough & John Helyar (book cover)

    Barbarians at the Gate

    Bryan Burrough & John Helyar

    The RJR Nabisco LBO.

    60%
  14. A Promised Land — Barack Obama (book cover)

    A Promised Land

    Barack Obama

    Presidential memoir, volume one.

    40%

Runner Frontier — My personal running log

I built Runner Frontier to turn PRs into a continuous frontier. I didn't want my progress to be defined only by arbitrary benchmarks like my one-mile, two-mile, or 5K times. I wanted to measure my improvement over time, in my own way. You can see a summary of my data in the cards below or look at the graph with the raw data here →.

Runner Frontier graph plotting running pace against distance, with monthly run points and the frontier highlighted Runner Frontier preview Pace × distance, run by run Open the live graph
Latest verified snapshot Jan 5 → Oct 2 / 2026
Total distance 266.5miles
Runs logged 121
Time moving 43h 12m

2026 by month

Mileage / runs
Jan17.8 mi10 runs
Feb19.8 mi12 runs
Mar26.0 mi18 runs
Apr32.2 mi15 runs
May27.7 mi11 runs
Jun42.6 mi16 runs
Jul44.5 mi15 runs
Aug31.8 mi13 runs
Sep22.2 mi10 runs
Oct2.0 mi1 run

Personal records

All time
Fastest 1 mi+ 7:02/mi

1.0 mi · Sep 7

Fastest 2 mi+ 8:04/mi

2.0 mi · Oct 2

Fastest 5K+ 9:16/mi

3.3 mi · Apr 15

Fastest 4 mi+ 9:34/mi

4.0 mi · May 2

Longest run 6.1 mi

10:50/mi · Jul 2

First run Jan 5

1.2 mi · 10:04/mi

Most recent Tier 1 2.0 mi

8:04/mi · Oct 2

Latest entries

  1. 2.0 miles
    Time
    16:12
    Pace
    8:04/mi
  2. 2.4 miles
    Time
    19:55
    Pace
    8:29/mi
  3. 3.3 miles
    Time
    31:02
    Pace
    9:31/mi
  4. 2.5 miles
    Time
    22:24
    Pace
    8:56/mi