Open WebUI
@OpenWebUI
Followers
10K
Following
632
Media
32
Statuses
346
The freedom AI stack.
localhost
Joined December 2023
the headline in openclaw 3.24 for me: Open WebUI finally works like a real frontend. before this, the OpenAI-compatible layer was the weak link. tool_call_id duplicates, strict field errors on non-native providers, prompt_cache breakage - you'd debug the bridge instead of the
5
15
98
OpenClaw 2026.3.24 🦞 🔌 Improved OpenAI API: talk to sub-agents with @openwebui 🎛️ Skill & tool management Control UI 🎨 Slack interactive reply buttons 💅 Native Microsoft Teams 🧵 Smart Discord auto-thread naming Any client. Any model. One runtime.
github.com
Breaking Changes Gateway/OpenAI compatibility: add /v1/models and /v1/embeddings, and forward explicit model overrides through /v1/chat/completions and /v1/responses for broader client and RAG com...
243
255
2K
🤝 Hello native subagents from @openclaw inside @OpenWebUI. We revamped our OpenAI compatible API to give sub-agent level chat support in todays build. Image and speech is coming soon 💅
6
13
106
Private AI infra is becoming the default. GPU inference → API layer → UI Here’s a practical guide using Open WebUI + vLLM on Hot Aisle (MI300X) to build a private ChatGPT-style system: https://t.co/DN2cLbO6NL
@HotAisle @AIatAMD @AMD @OpenWebUI @vllm_project
hotaisle.xyz
Step-by-step guide to building a private ChatGPT-style interface using Open WebUI connected to a self-hosted vLLM server on Hot Aisle. Includes SSH tunneling and architecture overview.
3
2
18
We have to acknowledge that @OpenWebUI + open terminal with @MistralAI 4 small is a game changer for AI sovereignty. Well done to both of you.
0
1
5
I've drop-in solution called Ovllm. It's essentially an Ollama-style wrapper, but for vLLM instead of llama.cpp. It's still a work in progress; it downloads models directly from Hugging Face. @vllm_project @OpenWebUI
https://t.co/rSQWdJmydq OpenWebUi Compatible
github.com
is a user-friendly wrapper around [vLLM] that provides Ollama-like simplicity for downloading and serving LLM models from HuggingFace. It's designed to work seamlessly with [OpenWebUI] - Fe...
1
1
6
The Qwen 3.5 small model series is now available ollama run qwen3.5:9b ollama run qwen3.5:4b ollama run qwen3.5:2b ollama run qwen3.5:0.8b All models support native tool calling, thinking, and multimodal capabilities in Ollama.
🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast,
97
366
3K
Me realising I can run these models locally on my M1 MacBook Air for free https://t.co/oN2dyoXxbJ
🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast,
76
350
7K
Running local models shouldn’t be complicated. OpenWebUI now auto-detects Docker Model Runner for a self-hosted setup in minutes. Enable Model Runner, start OpenWebUI, and your models are live in the browser. No extra config, no cloud required. 📖
docker.com
Run self-hosted models in minutes. OpenWebUI auto-detects Docker Model Runner. No configuration required so you can chat with local models from a modern web UI.
7
16
138
Get @OpenWebUI before shit hits the fan. https://t.co/XmCw7a87XD
github.com
[0.8.0] - 2026-02-12 Caution⚠️ Database Migrations: This release includes database schema changes; we strongly recommend backing up your database and all associated data before upgrading in product...
I’m selling ad space on my toilet until I reach $1,000,000 And thanks to @OpenWebUI—the best way to keep your AI girlfriend secure—only $976,000 left to go This is million dollar toilet:
0
2
12
LM StudioとOpen webUI繋げてみた。 Ryzen AI Max*395でQwen3-vl-30b-a3bを使うと、TTFTは遅いけど、処理自体はそこそこ速い。 内容と日本語は完璧。
1
1
7
1
1
20
Why is the AWS outage affecting you? I thought you were decentralized?
545
2K
21K
Run local LLMs with a richer UI, not just CLI. Docker Captain Sergei Shitikov built Open WebUI for Docker Desktop, an extension that installs and connects Open WebUI with Docker Model Runner in just a few clicks. Try it in the Extensions Marketplace. https://t.co/bYpkvuJVzy
docker.com
Use the Open WebUI extension for Docker Desktop to run local LLMs with Docker Model Runner—chat UI, file uploads, voice, and multi-model support in minutes.
2
11
81
My PARENTAL CONTROL ----> Don't give my kids ChatGPT At least not like this. I want more control. @OpenWebUI solves this for me. I walk you through how to set it up in this video:
Introducing parental controls in ChatGPT. Now parents and teens can link accounts to automatically get stronger safeguards for teens. Parents also gain tools to adjust features & set limits that work for their family. Rolling out to all ChatGPT users today on web, mobile soon.
4
5
90