sparkDash on the LAN + a Glance widget for it
Deployed sparkDash (multi-DGX-Spark monitoring) to the head Spark node and wired it into Glance. Notes to self so I remember the shape.
Posts by Tag
- homelab 4
- security 2
- ai-agent 2
- dgx-spark 2
- neovim 1
- lua 1
- jekyll 1
- ruby 1
- Cloudflare 1
- Caddy 1
- Parallel Simulation 1
- GPU 1
- Jax 1
- Prefix Sum 1
- X-sigma-rho 1
- Correlation 1
- Portfolio Construction 1
- Deepseek R1 1
- Hermes Agent 1
- 1Password 1
- API keys 1
- secrets management 1
- devops 1
- Home Assistant 1
- AI agent 1
- Frigate 1
- Alarmo 1
- camera 1
- smart home 1
- hermes-agent 1
- volcengine 1
- tts 1
- stt 1
- 火山引擎 1
- 豆包 1
- 语音合成 1
- zotero 1
- agent-skills 1
- arxiv 1
- google-scholar 1
- open-source 1
- python 1
- research-workflow 1
- self-hosting 1
- llama-cpp 1
- qwen 1
- llm 1
- glance 1
- monitoring 1
- sparkdash 1
- local-ai 1
- quantization 1
- deepseek 1
- speculative-decoding 1
homelab
Fitting Qwen3.8-27B with 128K Context on a 24GB TITAN RTX: A Self-Hosting Tuning Journey
My agent (Hermes, running on a Mac mini in the house) was “hanging” whenever it talked to my freshly deployed local model server. The server was up, health c...
Setting Up Caddy for Reverse Proxy with Cloudflare on Non-Standard Port
In this tutorial, we will walk through the steps to set up Caddy as a reverse proxy server and configure Cloudflare to communicate with your origin server us...
security
ai-agent
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
dgx-spark
Does Running an AI Model Locally Actually Hurt Its Quality?
Does Running an AI Model Locally Actually Hurt Its Quality?
sparkDash on the LAN + a Glance widget for it
Deployed sparkDash (multi-DGX-Spark monitoring) to the head Spark node and wired it into Glance. Notes to self so I remember the shape.
neovim
Journey to the Moon
I am crazy about vim and especially vim binding. However, configuring VIM in the old days of vimscript is just beyond me.
lua
Journey to the Moon
I am crazy about vim and especially vim binding. However, configuring VIM in the old days of vimscript is just beyond me.
jekyll
Note to Self: How to work with this site
Local Develop and Preview Install Ruby and Jekyll Follow this post
ruby
Note to Self: How to work with this site
Local Develop and Preview Install Ruby and Jekyll Follow this post
Cloudflare
Setting Up Caddy for Reverse Proxy with Cloudflare on Non-Standard Port
In this tutorial, we will walk through the steps to set up Caddy as a reverse proxy server and configure Cloudflare to communicate with your origin server us...
Caddy
Setting Up Caddy for Reverse Proxy with Cloudflare on Non-Standard Port
In this tutorial, we will walk through the steps to set up Caddy as a reverse proxy server and configure Cloudflare to communicate with your origin server us...
Parallel Simulation
Parallel Simulation of Linear Recurrence Relations via Prefix Sum
This post explores a clever algorithm by Guy Blelloch for simulating linear recurrence relations in parallel.
GPU
Parallel Simulation of Linear Recurrence Relations via Prefix Sum
This post explores a clever algorithm by Guy Blelloch for simulating linear recurrence relations in parallel.
Jax
Parallel Simulation of Linear Recurrence Relations via Prefix Sum
This post explores a clever algorithm by Guy Blelloch for simulating linear recurrence relations in parallel.
Prefix Sum
Parallel Simulation of Linear Recurrence Relations via Prefix Sum
This post explores a clever algorithm by Guy Blelloch for simulating linear recurrence relations in parallel.
X-sigma-rho
Back to Top ↑Correlation
Back to Top ↑Portfolio Construction
Back to Top ↑Deepseek R1
Back to Top ↑Hermes Agent
Back to Top ↑1Password
Back to Top ↑API keys
Back to Top ↑secrets management
Back to Top ↑devops
Back to Top ↑Home Assistant
Back to Top ↑AI agent
Back to Top ↑Frigate
Back to Top ↑Alarmo
Back to Top ↑camera
Back to Top ↑smart home
Back to Top ↑hermes-agent
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
volcengine
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
tts
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
stt
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
火山引擎
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
豆包
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
语音合成
给 Hermes Agent 接入火山引擎豆包语音：中文 TTS/STT 插件教程
Hermes Agent 是一个开源的 AI Agent 框架，支持在 Discord、Telegram、iMessage 等平台上运行。默认自带 Edge TTS 和 local whisper，但要获得高质量中文语音，火山引擎的豆包语音是目前的最优解。
zotero
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
agent-skills
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
arxiv
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
google-scholar
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
open-source
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
python
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
research-workflow
zotero-smart-ingest: An Agent Skill That Puts Papers in Zotero (With PDFs, No Duplicates)
I read a lot of finance papers. My workflow used to be: find paper → try to download PDF from five different places → manually create a Zotero entry → attach...
self-hosting
Fitting Qwen3.8-27B with 128K Context on a 24GB TITAN RTX: A Self-Hosting Tuning Journey
My agent (Hermes, running on a Mac mini in the house) was “hanging” whenever it talked to my freshly deployed local model server. The server was up, health c...
llama-cpp
Fitting Qwen3.8-27B with 128K Context on a 24GB TITAN RTX: A Self-Hosting Tuning Journey
My agent (Hermes, running on a Mac mini in the house) was “hanging” whenever it talked to my freshly deployed local model server. The server was up, health c...
qwen
Fitting Qwen3.8-27B with 128K Context on a 24GB TITAN RTX: A Self-Hosting Tuning Journey
My agent (Hermes, running on a Mac mini in the house) was “hanging” whenever it talked to my freshly deployed local model server. The server was up, health c...
llm
Fitting Qwen3.8-27B with 128K Context on a 24GB TITAN RTX: A Self-Hosting Tuning Journey
My agent (Hermes, running on a Mac mini in the house) was “hanging” whenever it talked to my freshly deployed local model server. The server was up, health c...
glance
sparkDash on the LAN + a Glance widget for it
Deployed sparkDash (multi-DGX-Spark monitoring) to the head Spark node and wired it into Glance. Notes to self so I remember the shape.
monitoring
sparkDash on the LAN + a Glance widget for it
Deployed sparkDash (multi-DGX-Spark monitoring) to the head Spark node and wired it into Glance. Notes to self so I remember the shape.
sparkdash
sparkDash on the LAN + a Glance widget for it
Deployed sparkDash (multi-DGX-Spark monitoring) to the head Spark node and wired it into Glance. Notes to self so I remember the shape.
local-ai
Does Running an AI Model Locally Actually Hurt Its Quality?
Does Running an AI Model Locally Actually Hurt Its Quality?
quantization
Does Running an AI Model Locally Actually Hurt Its Quality?
Does Running an AI Model Locally Actually Hurt Its Quality?
deepseek
Does Running an AI Model Locally Actually Hurt Its Quality?
Does Running an AI Model Locally Actually Hurt Its Quality?
speculative-decoding
Does Running an AI Model Locally Actually Hurt Its Quality?
Does Running an AI Model Locally Actually Hurt Its Quality?