# Self-Hosted AI

Published articles for Self-Hosted AI.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Open WebUI v0.11.1 Adds Human-in-the-Loop Tool Approval

DevFeed: [Open WebUI v0.11.1 Adds Human-in-the-Loop Tool Approval](<https://devfeed.tech/articles/open-webui-v0-11-1-adds-human-in-the-loop-tool-approval-10725.md>)

Original publisher: [Read original article](<https://selfhostlab.io/open-webui-v0-11-1-human-in-the-loop/>)

Author: Christian Rakoot

Published: 2026-08-30T06:34:36Z

Content type: article

Language: en

Sources: [Self Host Lab](<https://devfeed.tech/sources/self-host-lab.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Terminal](<https://devfeed.tech/topics/terminal.md>), [Homelab](<https://devfeed.tech/topics/homelab.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [homelab](<https://devfeed.tech/tags/homelab.md>), [news](<https://devfeed.tech/tags/news.md>), [news-self-hosted-ai](<https://devfeed.tech/tags/news-self-hosted-ai.md>), [open-webui](<https://devfeed.tech/tags/open-webui.md>), [release](<https://devfeed.tech/tags/release.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [self-hosted-ai](<https://devfeed.tech/tags/self-hosted-ai.md>)

### AI overview

Open WebUI v0.11.1 adds human-in-the-loop approval for selected AI tool calls, allowing users to review actions before execution. The release also fixes terminal-attached chat failures and two calendar timezone-related bugs.

### Source excerpt

Open WebUI v0.11.1 adds human-in-the-loop tool approval, letting you manually confirm certain tool calls before the AI runs them. The release also fixes chats with an attached personal terminal, plus two calendar bugs: new events now default to today's date, and recurring events finally display at the time you actually configured, not a miscalculated one.

## I Built a 256GB Local AI Cluster on My Desk

DevFeed: [I Built a 256GB Local AI Cluster on My Desk](<https://devfeed.tech/articles/i-built-a-256gb-local-ai-cluster-on-my-desk-10592.md>)

Original publisher: [Read original article](<https://technotim.com/posts/local-ai-gx10/>)

Author: Techno Tim

Published: 2026-05-18T13:00:00Z

Content type: article

Language: en

Sources: [Techno Tim](<https://devfeed.tech/sources/techno-tim.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Homelab](<https://devfeed.tech/topics/homelab.md>), [coding](<https://devfeed.tech/topics/coding.md>), [model-serving](<https://devfeed.tech/topics/model-serving.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [networking](<https://devfeed.tech/topics/networking.md>), [Docker](<https://devfeed.tech/topics/docker.md>), [NCCL](<https://devfeed.tech/topics/nccl.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [docker](<https://devfeed.tech/tags/docker.md>), [github](<https://devfeed.tech/tags/github.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [homelab](<https://devfeed.tech/tags/homelab.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [model-serving](<https://devfeed.tech/tags/model-serving.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [nccl](<https://devfeed.tech/tags/nccl.md>), [networking](<https://devfeed.tech/tags/networking.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [self-hosted-ai](<https://devfeed.tech/tags/self-hosted-ai.md>), [server](<https://devfeed.tech/tags/server.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### AI overview

The article tests a two-node local AI cluster built from ASUS Ascent GX10 systems, using one machine for practical agentic coding and two machines to run a larger local model. It evaluates a real coding workflow involving model serving, storage, networking, memory, Docker, NCCL, monitoring, power draw, and the application being built, concluding that local AI is capable and cloud-independent but still operationally complex.

### Source excerpt

I have been covering local and self-hosted AI for a few years now - from running models privately at home to what is still running in my homelab today. But to run the larger, more capable models, you need something more specialized than a general-purpose home server. I wanted to know how good local AI has actually gotten, so I built a mini AI cluster on my desk and used it for a real coding wo...

## How to Self-Host Your Own Private AI Stack

DevFeed: [How to Self-Host Your Own Private AI Stack](<https://devfeed.tech/articles/how-to-self-host-your-own-private-ai-stack-10508.md>)

Original publisher: [Read original article](<https://technotim.com/posts/ai-stack-tutorial/>)

Author: Techno Tim

Published: 2024-07-08T13:00:00Z

Content type: tutorial

Language: en

Sources: [Techno Tim](<https://devfeed.tech/sources/techno-tim.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Self-hosted](<https://devfeed.tech/topics/self-hosted.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Docker Compose](<https://devfeed.tech/topics/docker-compose.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [traefik](<https://devfeed.tech/topics/traefik.md>), [Ubuntu](<https://devfeed.tech/topics/ubuntu.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [docker](<https://devfeed.tech/tags/docker.md>), [homelab](<https://devfeed.tech/tags/homelab.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [self-hosted-ai](<https://devfeed.tech/tags/self-hosted-ai.md>), [traefik](<https://devfeed.tech/tags/traefik.md>), [ubuntu](<https://devfeed.tech/tags/ubuntu.md>)

### AI overview

A tutorial for running a local, private, self-hosted AI stack. It covers hardware considerations, Ubuntu Server 24.04 LTS, NVIDIA drivers, Docker Compose services, Traefik reverse-proxy access, internal DNS, and optional basic authentication for Ollama.

### Source excerpt

In this tutorial we'll walk through my local, private, self-hosted AI stack so that you can run it too. 📺 Watch Video Disclosures Nothing in this video was sponsored Info If you're looking for the overview of this stack, you can out the video here Self-Hosted AI That's Actually Useful Hardware Machine Used for AI: Building My ULTIMATE, All-inOne, HomeLab Server GPUs Here are ...