RunAnywhere SDK
Shares rank 16 of 27 inference engines by recommenders
People praise its fast on-device inference and STT-LLM-TTS latency; critics raise spam outreach and exposed API keys.
People praise its fast on-device inference and STT-LLM-TTS latency; critics raise spam outreach and exposed API keys.
22 people gave an opinion
- recommend it
- 9
- criticize it
- 13
- approval share
- 41%
Recommended in 2 of 13 months
- November 2025: not 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: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 0.6 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not 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
Fast STT-LLM-TTS pipeline latency
“The latency improvements for the STT-LLM-TTS pipeline look incredible.”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “Latency is killer in the STT-LLM-TTS pipeline.”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “The inference engine (MetalRT) is production-grade, the pipeline architecture is solid, but the models at this size are still the weak link for complex tool routing.”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” Matches projects people want to build
“this is a tremendous achievement and it's extremely relevant in the OpenClaw world”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “we're trying to show whats possible today on their hardware”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “Amazing, this is what I am trying to do”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon”
What people warn about
Each mark is one comment
Install and load failures reported
“not everything is loading properly when installed via homebrew”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “on their github they just pushed an update to say that it didn't work M3 and M4.”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “This doesn't work on any of the methods I've tried.”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” - Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon”
- Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon”
Spam emails and lookalike domains
“they are a company that registers domains similar to their main one, and then uses those domains to spam people”
Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “they're intentionally registering these "alternate" domains specifically for spam”
Comment from 26 Feb 2026 in “Tell HN: YC companies scrape GitHub activity, send spam emails to users” “this is the company that cold emailed many people via email on GitHub”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” - Comment from 10 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon”
Exposed API keys in demo
“I can still see the API keys in https://www.runanywhere.ai/web-demo , FWIW.”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “Seems like you are leaking an ElevenLabs API key in your web demo.”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “Accepting the mistake and fixing the leak altogether would have been the better way to handle this.”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” Poor response to criticism
“Accepting the mistake and fixing the leak altogether would have been the better way to handle this.”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “These responses to constructive feedback show an immature team full of hubris.”
Comment from 11 Mar 2026 in “Show HN: RunAnwhere – Faster AI Inference on Apple Silicon” “This is a really bad look on them.”
Comment from 26 Feb 2026 in “Tell HN: YC companies scrape GitHub activity, send spam emails to users”
Other inference engines people recommend
The four most recommended other inference engines, 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 |
|---|---|---|---|---|---|---|
| vLLM | 112 | 56 | 67% | 12 | — | Approved |
| Strata | 31 | 15 | 67% | 5 | — | Approved |
| DwarfStar 4 | 26 | 2 | 93% | 6 | — | Approved |
| SGLang | 19 | 13 | 59% | 8 | — | — |
| RunAnywhere SDKThis page | 9 | 13 | 41% | 2 | — | — |
What people said
27 of the 29 comments that mention it, newest first. Each links to the original comment.
“please check our main repo”
“The inference engine (MetalRT) is production-grade, the pipeline architecture is solid, but the models at this size are still the weak link for complex tool routing.”
“I can still see the API keys in https://www.runanywhere.ai/web-demo , FWIW.”
“These responses to constructive feedback show an immature team full of hubris.”
“Accepting the mistake and fixing the leak altogether would have been the better way to handle this.”
“we're trying to show whats possible today on their hardware”
“the model hallucinated success instead of routing to the open_url tool”
“this is the company that cold emailed many people via email on GitHub”
“Seems like you are leaking an ElevenLabs API key in your web demo.”
“It does tries to have some memory management done too - to remember previous context”
“The latency improvements for the STT-LLM-TTS pipeline look incredible.”
“It loads after those errors.”
“the TTS sounds like it's 10 years out of date”
“This doesn't work on any of the methods I've tried.”
“This option didn't work either. I tried it.”
“this is a tremendous achievement and it's extremely relevant in the OpenClaw world”
“on their github they just pushed an update to say that it didn't work M3 and M4.”
“This is not different from mlx-lm other than it uses a closed-source inference engine.”
“This looks vibecoded? There's reference to an account that doesn't exist on my machine.”
“Amazing, this is what I am trying to do”
“Don't give RunAnywhere your GitHub”
“they are a company that registers domains similar to their main one, and then uses those domains to spam people”
“not everything is loading properly when installed via homebrew”
“Latency is killer in the STT-LLM-TTS pipeline.”
“I tried their sdks, it's great! and I've been loving their apps as well.”
“This is a really bad look on them.”
“they're intentionally registering these "alternate" domains specifically for spam”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.