yujonglee
Re:Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer a...
on Wednesday October 21, 2026 @09:13PM (#50189878)
Re:Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer a...
on Wednesday October 21, 2026 @02:47PM (#50185671)
This incident is unrelated to what was committed to the repository.
More info: https://docs.litellm.ai/blog/security-incident-oct-21-2026
Re:Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer a...
on Wednesday October 21, 2026 @02:42PM (#50185595)
Official Incident Post: https://docs.litellm.ai/blog/security-incident-oct-21-2026
Re:Litelm: LiteLLM Without the Bloat
on Friday September 11, 2026 @07:51PM (#49667017)
- We recently migrated to shadcn, which also comes with dark mode support.
- You can subscribe to the issue or email me at yujong at berri.ai
I’m happy to provide any support if you’re willing to try out the initial version.
Re:Litelm: LiteLLM Without the Bloat
on Friday September 11, 2026 @06:59PM (#49666594)
thanks for the feedback. genuinely curious what you think we could be doing better, especially around our dev practices. Would love to hear specifics.
Re:Litelm: LiteLLM Without the Bloat
on Friday September 11, 2026 @06:58PM (#49666579)
also if you had resource issues with your production deployment, keen to hear more details
Re:Litelm: LiteLLM Without the Bloat
on Friday September 11, 2026 @06:57PM (#49666571)
hey - litellm will migrate its core to Rust soon.
please follow this issue if you're interested! https://github.com/BerriAI/litellm/issues/31263
Re:Launch HN: Speko (YC S26) – OpenRouter for Voice AI
on Monday August 17, 2026 @03:41PM (#49336512)
cool! we have something similar implemented:
https://github.com/fastrepl/anarlog/tree/main/crates/owhispe...
Re:Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a ...
on Wednesday August 05, 2026 @06:21AM (#49180776)
amazing work! impressed with https://deepgrove.ai/chat
Re:The Conductor Rewrite: What They Changed to Make It Fast
on Wednesday June 24, 2026 @01:07AM (#48655400)
there is some overlap on how I built relay plugin:
https://yujonglee.com/blog/hacking-tauri-for-designer/
Source code: https://github.com/fastrepl/anarlog/tree/d38413681a3c02f5ba3...
Re:Show HN: Compile-time model-id validation with declared capability
on Tuesday May 26, 2026 @10:21AM (#48280245)
fyi this use vendored openrouter models info:
https://github.com/yujonglee/openrouter-toolkit/blob/main/cr...
Show HN: Compile-time model-id validation with declared capability
Show HN: Composable CLI for your meeting workflow
Hi, this is Yujong from Char (https://github.com/fastrepl/char).This CLI is a repackaging of the audio/transcription pipeline that powers our desktop app. We noticed that some people build lightweight CLIs to record conversations and send them to tools like OpenClaw or other agents for transcription and workflow automation, so we wanted to make this more accessible as a standalone tool.It...
Hacking Tauri for Designer
Re:We Shipped 100 Hardware Units in Under Eight Weeks for YC S25 Demo Day
on Friday September 19, 2025 @12:40PM (#45303669)
Super impressed and inspired!
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Friday August 15, 2025 @01:35PM (#44915170)
kind of self-plug, but you might find https://github.com/fastrepl/hyprnote/blob/main/README.md interesting.
EDIT: typo
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Friday August 15, 2025 @02:59AM (#44909370)
It can run Whisper and Moonshine models locally, while also allowing the use of other API providers. Read the docs - or at least this post.
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Friday August 15, 2025 @01:47AM (#44909014)
what do you mean? this use-case is not llm. it is realtime stt.
also fyi - https://docs.hyprnote.com/owhisper/configuration/providers/o...
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @10:20PM (#44907931)
sure. `owhisper pull --help`
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @09:08PM (#44907568)
yes. metal is on
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @08:34PM (#44907368)
Thank you!
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @07:53PM (#44907103)
Its lot more than that.
- It supports other models like moonshine.
- It also works as proxy for cloud model providers.
- It can expose local models as Deepgram compatible api server
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @07:51PM (#44907089)
probably end of this month or early next month. not 100% sure.
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @07:51PM (#44907087)
we store data in R2 and range query sometime glitch...
It might work if you retry it
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @05:24PM (#44905874)
yeah we use whisper.cpp for whisper inference. this is more like a community-focused project, not a commercial product!
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @05:19PM (#44905820)
got it. fyi if you run `owhisper pull --help`, this info is printed
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @04:54PM (#44905593)
It's open-source. Happy to review & merge if you can send us PR!
https://github.com/fastrepl/hyprnote/blob/8bc7a5eeae0fe58625...
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @04:36PM (#44905400)
Are you thinking about the realtime use-case or batch use-case?
For just transcribing file/audio,
`owhisper run <MODEL> --file a.wav` or
`curl httpsL//something.com/audio.wav | owhisper run <MODEL>`
might makes sense.
Re:Show HN: OWhisper – Ollama for realtime speech-to-text
on Thursday August 14, 2025 @04:29PM (#44905313)
This is CLI entry point:
https://github.com/fastrepl/hyprnote/blob/8bc7a5eeae0fe58625...