HackerTrans
トップ新着トレンドコメント過去質問紹介求人

tpae

290 カルマ登録 15 年前

投稿

Show HN: Osaurus – Ollama-Compatible Runtime for Apple Foundation Models

github.com
6 ポイント·投稿者 tpae·9 か月前·2 コメント

Show HN: Tweaks – Copy → Tweak – 2 MB macOS AI Clipboard App (MIT License)

github.com
1 ポイント·投稿者 tpae·9 か月前·0 コメント

コメント

tpae
·昨日·議論
I'm working on Osaurus, AI harness for local models. It's for macOS, written in Swift.

https://github.com/osaurus-ai/osaurus
tpae
·4 日前·議論
Open source would make them an instant credible leader, major fumble (still can be fixed)
tpae
·29 日前·議論
I've been building native macOS harness called Osaurus https://osaurus.ai/

It's full featured with agent loop, gets work done locally.

It's open-source and Swift-based, we built our own inferencing engine since every other engine is based on Python. Check us out - https://github.com/osaurus-ai/osaurus

Looking for some feedback!
tpae
·5 か月前·議論
just fixed it
tpae
·5 か月前·議論
The framing here assumes you need to ship native to all 3 platforms to justify leaving Electron. You don't.

I've been building a native macOS AI client in Swift — it's 15MB, provider-agnostic, and open source: https://github.com/dinoki-ai/osaurus

Committing to one platform well beats a mediocre Electron wrapper on all three.
tpae
·6 か月前·議論
You can check out my project here: https://github.com/dinoki-ai/osaurus

I'm focused on building it for the macOS ecosystem
tpae
·7 か月前·議論
I'm working on https://github.com/dinoki-ai/osaurus, Native macOS LLM server with MCP support. Looking for more feedback!
tpae
·8 か月前·議論
This looks cool. I actually created Tweaks - https://tweaks.io/
tpae
·8 か月前·議論
I've been building with local AI, on Apple Silicon. It's only 8mb, but runs 30% faster than Ollama.

https://github.com/dinoki-ai/osaurus
tpae
·9 か月前·議論
Not yet, but can be supported in the future
tpae
·9 か月前·議論
I just finished https://tweaks.io, it's open-source and MIT licensed. Let me know your thoughts!
tpae
·10 か月前·議論
I'm working on Osaurus - https://github.com/dinoki-ai/osaurus, native, Apple Silicon–only local LLM server. Open Source + MIT-License
tpae
·10 か月前·議論
Check out Osaurus - MIT Licensed, native, Apple Silicon–only local LLM server - https://github.com/dinoki-ai/osaurus
tpae
·11 か月前·議論
Location: Los Angeles, CA

Remote: Yes

Willing to relocate: No

Technologies: React, TypeScript, Next.js, SwiftUI, GraphQL, Node.js, OpenAI APIs, RAG, LLM agents, macOS/iOS dev

Résumé/CV: Available upon request

Email: [email protected]

Staff-level engineer (15+ yrs) with experience across FAANG and startups. I specialize in shipping polished UIs fast, integrating AI features (LLMs, agents, RAG), and designing user-first tools. Previously led frontend/product at an acquired no-code platform (100K+ users), built an Apple-featured app solo, and currently building AI-native desktop companions.

Seeking freelance/contract work only — early product, creative tools, or AI interfaces preferred.
tpae
·12 か月前·議論
Location: Los Angeles, CA

Remote: Yes

Willing to relocate: No

Technologies: React, TypeScript, Next.js, SwiftUI, GraphQL, Node.js, OpenAI APIs, RAG, LLM agents, macOS/iOS dev

Résumé/CV: Available upon request

Email: [email protected]

Staff-level engineer (15+ yrs) with experience across FAANG and startups. I specialize in shipping polished UIs fast, integrating AI features (LLMs, agents, RAG), and designing user-first tools. Previously led frontend/product at an acquired no-code platform (100K+ users), built an Apple-featured app solo, and currently building AI-native desktop companions.

Seeking freelance/contract work only — early product, creative tools, or AI interfaces preferred.
tpae
·2 年前·議論
No thanks. I've applied every year for the first ten years since I was 20 and have not received any feedback on my rejections. The only times I did not apply, I went on to raise series A & B. I've seen friends get accepted with nothing but an idea and a Stanford degree.