Sahil Jagtap
Contact LinkedIn GitHub Twitter Chat Video
I'm a token billionaire - I spend a lot of them. Artificially intelligent. I build companies too: founded three. My last one, Airstitch, got acquired. My open-source library for keeping AI agents from burning through their budget, AgentBudget, has 100k+ installs. Right now I'm helping PE firms not lose the plot - building something cool (still quiet) with my two cofounders, who actually know private capital. Previously CTO at Airstitch, AgentBudget, and HomePlate. I always reply.
What I'm building
Something new (in stealth) - I'm building software that helps private capital firms turn scattered deal data - PDFs, spreadsheets, data rooms, email - into better, defensible investment decisions, starting with distressed debt. More soon.
AgentBudget (demos) - I made it. It's a ulimit for AI agents: it stops a single agent run from blowing through your whole API budget. 100k+ installs, 100+ GitHub stars, now run by the community. There's a whitepaper on the design.
Airstitch (acquired) - an AI chief of staff that lived inside iMessage, SMS, and WhatsApp, so there was no new app to learn. 200+ users, 20 paying in the first 9 days. Built at Founders Inc (Artifact'26). Then it got acquired.
HomePlate - I was CTO and co-founder. Medical meal delivery for seniors: we turned licensed senior kitchens into on-demand, medically-tailored meal prep for people whose chronic illness dictates what they can eat. $4,000 across the first 10 pilots, covered by Fox News.
Barty (didn't work out) - an AI recruiter that screened candidates and ran interview workflows. It won $8,000 at George Mason's Patriot Pitch competition but never found a market. It taught me how B2B sales actually work - the gap between loving a demo and paying for it - which is how I built Airstitch.
Earlier work
NSF wearables research (George Mason) - lead ML engineer. Built the pipeline for spotting early cognitive decline from how people move, using wearable sensor data. 87% accuracy, 500+ participants. Paper going to CHI 2026; talk at NARRTC 2026.
Cerebras - engineering fellow. Built AI agents on their inference chips.
Microsoft - student researcher. Built ML pipelines over satellite radar data for environmental monitoring.
Trigent - software engineer (intern). Built a computer-vision system for FDA-regulated medical imaging and a HIPAA-compliant pipeline for 200K+ patient records.
Zepto - I did delivery runs in India myself to learn last-mile logistics first-hand instead of from a dashboard. Found 3 friction points each costing 15+ minutes a delivery.
NYC startup rescue - fixed a production bug that had stalled a startup's revenue. They recovered.
Open source beyond AgentBudget: contributions to LangChain, Supabase, LangFuse, and Scribe, plus a hackathon-winning swimmer-tracking model that used only motion sensors - no GPS, no cameras (Devpost).
Recognition
Won HackMIT, HackPrinceton, and PennApps (2023 & 2024) out of 30+ hackathons. Patriot Pitch 1st place ($8K). Mason Distinction Award ($84K scholarship). Part of Founders Inc Artifact'26 and NVIDIA Inception.
I've judged hackathons at NASA TechRise, Technica, UVA HooHacks, and UMD Bitcamp, and I ran George Mason's Data Science & Computation Society - grew it from under 30 members to 500+.
CS @ George Mason University · GitHub · LinkedIn · X · Email · AgentBudget
Side experiments
Poop - tried to create a clothing brand. Sometimes you just have to see what happens.