Osaurus
Shares rank 21 of 27 local LLM runners by recommenders
A free, open-source, local-first macOS app for running AI models and agents, recommended for being small, fast and provider-agnostic.
A free, open-source, local-first macOS app for running AI models and agents, recommended for being small, fast and provider-agnostic.
6 people gave an opinion
- recommend it
- 6
- criticize it
- 0
- approval share
- 100%
Recommended in 6 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Open source and provider-agnostic
“It's open-source and Swift-based, we built our own inferencing engine since every other engine is based on Python.”
Comment from 14 Jun 2026 in “Ask HN: What are you working on? (June 2026)” “it's 15MB, provider-agnostic, and open source”
Comment from 21 Feb 2026 in “When Code is Free, Why is Claude is an Electron app?” “Open source, local-first, provider-agnostic.”
Comment from 2 Mar 2026 in “Ask HN: Who is hiring? (March 2026)” Enjoyable and good to use
“I prodded myself into playing with Osaurus; it's actually rather good.”
Comment from 27 Oct 2026 in “Show HN: Hob - Open-source, on device alternative to Claude Cowork and ChatGPT” “Your work is super awesome, love the osaurus tool!”
Comment from 14 Nov 2025 in “Launch HN: Tweeks (YC W25) – Browser extension to deshittify the web” “I've been having fun with this one”
Comment from 25 Mar 2026 in “Local LLM by Ente” Small download and fast
“It's only 8mb, but runs 30% faster than Ollama.”
Comment from 9 Nov 2025 in “Ask HN: What Are You Working On? (Nov 2025)” “it's 15MB, provider-agnostic, and open source”
Comment from 21 Feb 2026 in “When Code is Free, Why is Claude is an Electron app?” Privacy-focused and local-first
“Heavily privacy focused with e2ee iOS and iPadOS tethers.”
Comment from 26 Oct 2026 in “Show HN: Hob - Open-source, on device alternative to Claude Cowork and ChatGPT” “Open source, local-first, provider-agnostic.”
Comment from 2 Mar 2026 in “Ask HN: Who is hiring? (March 2026)”
Other local LLM runners people recommend
The four most recommended other local LLM runners, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| llama.cpp | 471 | 109 | 81% | 13 | 1 yr4 owners | Approved |
| Ollama | 350 | 247 | 59% | 12 | 1.5 yrs8 owners | — |
| LM Studio | 217 | 74 | 75% | 12 | 3 yrs4 owners | Approved |
| DS4 by antirez | 109 | 20 | 84% | 7 | 1 mo3 owners | Approved |
| OsaurusThis page | 6 | 0 | 100% | 6 | — | — |
What people said
9 of the 10 comments that mention it, newest first. Each links to the original comment.
“I prodded myself into playing with Osaurus; it's actually rather good.”
“Heavily privacy focused with e2ee iOS and iPadOS tethers.”
“It's open-source and Swift-based, we built our own inferencing engine since every other engine is based on Python.”
“native Swift macOS app with sandboxing, agent tooling, and server capabilities”
“I've been having fun with this one”
“Open source, local-first, provider-agnostic.”
“it's 15MB, provider-agnostic, and open source”
“Your work is super awesome, love the osaurus tool!”
“It's only 8mb, but runs 30% faster than Ollama.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.