# Tyler Darisme — a-Fig

I'm Tyler Darisme (a-Fig), a CS student at San José State University building at the intersection of AI tooling, full-stack web, and blockchain. I like building things, hopefully you like them too.

> Generated from the live homepage at https://afig.dev/ — see https://afig.dev/llms.txt for a shorter, curated overview.

[a-Fig](https://afig.dev/card)

Bay Area, California

Tyler
Darisme

Computer Science @ SJSU

I like building things, hopefully you like them too.

[ My Resume ](https://afig.dev/resume) [ My GitHub ](https://github.com/a-Fig) [ My LinkedIn ](https://www.linkedin.com/in/tyler-darisme-454011300)

Or email me directly at [tylerd2474@gmail.com](mailto:tylerd2474@gmail.com)

![Animated fig character dancing](https://afig.dev/assets/fig-dribbble.gif)

### Highlights

#### Awards & Contests

2nd — UC Berkeley AI Hackathon

2026 · sponsor track, best token compression (Accordion)

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

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.

Tech Officer — Competitive Programming Club

Sep 2025 – Feb 2026

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

### Projects

![Accordion — a visual map of an AI agent's context window](https://afig.dev/assets/accordion-hero.gif)

#### Accordion

[ 202 ](https://github.com/a-Fig/Accordion/stargazers) TypeScript — Types the folding engine, the Svelte desktop UI, and the pi extension that feeds it. Tauri — Wraps the SvelteKit UI in a native desktop shell, so the context map is a real app rather than a browser tab. pi-coding-agent — Hooks pi's extension API to rewrite the outgoing messages before every model call, so the GUI can fold a live session.

Accordion is a developer tool for context visualization and intelligent context management that replaces /compact. Where /compact erases history in one irreversible pass, Accordion folds individual blocks to cached summaries you can unfold instantly, and lets you pin the ones that must survive. An automated conductor handles the folding decisions by default, but you're always free to override it. My Thermocline conductor scored 83.3% vs 33.3% for naive compaction on SlopCodeBench. 2nd place, UC Berkeley AI Hackathon 2026.

[ GitHub ](https://github.com/a-Fig/Accordion) [ Live ](https://get-accordion.dev/)

#### Are You Smarter Than Claude?

2hr build — Designed, built, and deployed in about two hours at Anthropic's Claude Impact Lab. TypeScript — Types the Next.js app and the rules for all six games you play against Claude. Google Cloud Run — Deployed as a container, so there is no signup — open the link and play.

A small project I built at Anthropic's Claude Impact Lab in Palo Alto, meant to be a fun way to make AIs like Claude feel more real and less scary. You can play six different games against Claude, including Connect Four, Battleship, trivia, and Wordle Race, and see firsthand where it is surprisingly good and where it completely falls apart. The goal is to give people a more intuitive feel for Claude's strengths and weaknesses. Built with Next.js and TypeScript, and hosted on Google Cloud Run. No account needed to try it, just click the link and play.

[ GitHub ](https://github.com/a-Fig/are-you-smarter-than-claude) [ Live ](https://are-you-smarter-than-claude-123326946878.us-west1.run.app/)

#### AfterCart

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

I built AfterCart at Davis Hacks 2026: photograph a grocery receipt and it OCRs every line item, then tells you what the same basket costs at nearby stores — matching against a crowdsourced database of 18,649 price observations across 244 stores, on Postgres 16 with PostGIS + pgvector, Google Vision OCR, and Gemini 2.5 Flash.

[ GitHub ](https://github.com/a-Fig/aftercart-davis-hacks-2026) [ Live ](https://aftercart-web-407493014719.us-west1.run.app/)

#### Automated-Game-Bot

[ 25 ](https://github.com/a-Fig/Automated-Game-Bot/stargazers) Pre-AI — Built in 2024, before AI coding assistants were a major part of my workflow. Python — The whole bot: the detection loop, the game control, and the multiprocessing that runs them at once. PyAutoGUI — Drives the real mouse and keyboard, so the bot plays through the game client the way a person would. Computer Vision — Five YOLOv11 models read the screen live — resource nodes, mobs, obstacles, spell state, and health. Roboflow — Labeled and trained all five detection models there, and published every dataset publicly.

I built an autonomous Albion Online bot integrating five specialized detection models for resource farming, combat, spellcasting, obstacle avoidance, and real-time threat detection, using YOLOv11 and OpenCV for computer vision, PyAutoGUI for game control, with concurrent scanning and actions executed via multiprocessing.

Built in 2024, before AI coding assistants were a major part of my workflow.

[ GitHub ](https://github.com/a-Fig/Automated-Game-Bot) [ Watch ](https://www.youtube.com/watch?v=l8Mt02X6kl4)

#### Agent Trials

Python — Flask platform on Cloud Run serving every room, the HTTP action API, and the asynchronous benchmark grading.

A platform where AI agents compete over plain HTTP — no runtime to install, just game state in and actions out. Nine rooms spanning games and benchmarks, from Battleship with a weapon economy to code and long-context evals, with Elo matchmaking and browser spectating.

[ Live ](https://agent-trials-407493014719.us-west1.run.app/)

#### AceAnything

Python — The FastAPI backend that generates the quizzes and schedules the spaced repetition.

An AI quiz platform I built (FastAPI + Vue + Gemini) that generates adaptive quizzes on any subject with spaced repetition, instant explanations, and text-to-speech.

[ GitHub ](https://github.com/a-Fig/AceAnything) [ Live ](https://aceanything-407493014719.us-west1.run.app/)

#### Blackjack-On-Chain

Solidity — Seven modular contracts hold every rule of the game on-chain.

A decentralized blackjack dApp with seven modular smart contracts running all game logic on-chain, deployed on Arbitrum Sepolia.

[ GitHub ](https://github.com/a-Fig/Blackjack-On-Chain)

#### pi-mcp-server

TypeScript — The server itself: the MCP tool definitions bridging Claude Code and pi.

An MCP server I wrote to bridge Claude Code and the pi coding agent.

[ GitHub ](https://github.com/a-Fig/pi-mcp-server)

[ More on GitHub → ](https://github.com/a-Fig)

## Who am I

Books & runs

### What I'm reading

1.

![Steve Jobs — Walter Isaacson (book cover)](https://afig.dev/assets/books/steve-jobs.jpg)

#### Steve Jobs Reading now

Walter Isaacson

The authorized biography.

72%

2.

![Zero to One — Peter Thiel (book cover)](https://afig.dev/assets/books/zero-to-one.jpg)

#### Zero to One ★

Peter Thiel

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

100%

3.

![Breakneck — Dan Wang (book cover)](https://afig.dev/assets/books/breakneck.jpg)

#### Breakneck

Dan Wang

China's industrial policy & manufacturing.

100%

4.

![Nexus — Yuval Noah Harari (book cover)](https://afig.dev/assets/books/nexus.jpg)

#### Nexus

Yuval Noah Harari

Information networks, AI, human coordination.

100%

5.

![Business Adventures — John Brooks (book cover)](https://afig.dev/assets/books/business-adventures.jpg)

#### Business Adventures

John Brooks

Classic Wall Street case studies.

100%

6.

![Blitzscaling — Reid Hoffman (book cover)](https://afig.dev/assets/books/blitzscaling.jpg)

#### Blitzscaling

Reid Hoffman

Hypergrowth strategy.

100%

7.

![Atomic Habits — James Clear (book cover)](https://afig.dev/assets/books/atomic-habits.jpg)

#### Atomic Habits

James Clear

Habit systems.

100%

8.

![The Shock Doctrine — Naomi Klein (book cover)](https://afig.dev/assets/books/the-shock-doctrine.jpg)

#### The Shock Doctrine

Naomi Klein

Disaster capitalism.

100%

9.

![Poor Charlie's Almanack — Charlie Munger (book cover)](https://afig.dev/assets/books/poor-charlies-almanack.jpg)

#### Poor Charlie's Almanack

Charlie Munger

Mental models.

100%

10.

![The Essays of Warren Buffett — Lawrence A. Cunningham (book cover)](https://afig.dev/assets/books/the-essays-of-warren-buffett.png)

#### The Essays of Warren Buffett

Lawrence A. Cunningham

Buffett's shareholder letters, by theme.

100%

11.

![Barbarians at the Gate — Bryan Burrough & John Helyar (book cover)](https://afig.dev/assets/books/barbarians-at-the-gate.jpg)

#### Barbarians at the Gate

Bryan Burrough & John Helyar

The RJR Nabisco LBO.

60%

12.

![A Promised Land — Barack Obama (book cover)](https://afig.dev/assets/books/a-promised-land.jpg)

#### 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 →](https://runner-frontier-74255.web.app/).

[ ![Runner Frontier graph plotting running pace against distance, with monthly run points and the frontier highlighted](https://afig.dev/assets/runner-frontier-preview.png) Runner Frontier preview **Pace × distance, run by run** Open the live graph ](https://runner-frontier-74255.web.app/)

Stats pulled live from Runner Frontier Jan 5 → Jul 16 / 2026

Total distance **202.4miles**

Runs logged **94**

Time moving **32h 52m**

#### 2026 by month

Mileage / average pace

Jan**17.8 mi**9:41/mi avg

Feb**19.8 mi**9:09/mi avg

Mar**26.0 mi**9:21/mi avg

Apr**32.2 mi**9:05/mi avg

May**27.7 mi**9:45/mi avg

Jun**42.6 mi**10:17/mi avg

Jul**36.3 mi**10:20/mi avg

#### Personal records

All time

Fastest 1 mi+ **7:10/mi**

1.0 mi · May 4

Fastest 2 mi+ **8:09/mi**

2.0 mi · Apr 18

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 **5.5 mi**

10:17/mi · Jul 16

#### Latest entries

1. Jul**16** **5.5 miles**

**Time:** 56:48

**Pace:** 10:17/mi

2. Jul**14** **4.1 miles**

**Time:** 43:22

**Pace:** 10:39/mi

3. Jul**12** **3.0 miles**

**Time:** 31:00

**Pace:** 10:18/mi

4. Jul**09** **4.5 miles**

**Time:** 47:06

**Pace:** 10:27/mi

---

### get in touch

Tyler Darisme

Computer Science @ SJSU

- [aFig.dev](https://afig.dev/)
- [tylerd2474@gmail.com](mailto:tylerd2474@gmail.com)
- [linkedin.com/in/tyler-darisme-454011300](https://www.linkedin.com/in/tyler-darisme-454011300)
- [github.com/a-Fig](https://github.com/a-Fig)

© 2026 Tyler Darisme · a-Fig