tpae

tpae

OsaurusOsaurus
Making personal AI you actually own.
#251169221 followers4 following
#1,427Last month
29 KP
#7,036All time
921 KP

About

Founder of Osaurus, the open source AI harness for macOS. Local inference on Apple Silicon, agents, skills, and sandboxed execution. Previously shipped at Netflix, Tesla, and Zillow, and built NiftyKit (acquired). I believe inference is all you need. Everything else can be owned by you.

Badges

Top 5 Launch
Top 5 Launch
Tastemaker
Tastemaker
Veteran
Veteran
Gone streaking
Gone streaking
View all badges

Maker History

  • Osaurus
    OsaurusOpen source agents that run 100% locally on your Mac
    Jul 2026
  • NiftyKit
    NiftyKitYour No-Code Solution for NFTs
  • Froyo Party
    Froyo PartyThe anti-lonely real-time video chat app
    Apr 2020
    • 🎉
    Joined Product HuntJune 18th, 2015

Forums

Osaurusp/osaurus•

1mo ago

Projects: shared memory across every agent

We just shipped Projects in Osaurus and it fixes one of the oldest annoyances with AI chat apps: starting from zero every time.

Osaurusp/osaurus•

2mo ago

Your AI chat history is the new lock-in

Everyone talks about model lock-in, but the real switching cost is your conversation history. Months of context, decisions, and half-finished projects living inside one app.

We just shipped chat import in Osaurus (free, open source Mac app) so you can export your conversations from ChatGPT, Claude, Grok, Gemini, or Open WebUI and continue them with any model. Building it made us realize how differently each app treats your data on the way out. Some exports are clean JSON, some are a mess clearly not designed to be read by anything else.

Osaurusp/osaurus•

2mo ago

New in Osaurus: Browser Use, driven by a 9B local model

Osaurus agents can now drive a real browser. You give the agent a goal in plain language, and it navigates, clicks, reads pages, and reports back.

The demo we shipped it with: a 9B model checking an Amazon shopping cart. Real browser, real login, real cart. It signed in, read the page, and returned the items and prices. About 90 seconds, running locally on a Mac.

View more