b4rtazz
Show HN: AI workspaces for teams with human-AI interfaces
Re:Show HN: AilaFlow – AI workflow automation for teams with Human-AI ...
on Wednesday September 30, 2026 @02:33PM (#49912609)
This will be addressed in future versions. The plan is to serialise the definition for this specific version.
Re:Show HN: AilaFlow – AI workflow automation for teams with Human-AI ...
on Wednesday September 30, 2026 @08:58AM (#49908292)
Hi HN, I’m building AilaFlow, an AI workflow automation platform for teams or home usage with Human-AI interfaces.
I would love your feedback!
Get started: https://ailaflow.com/docs/ How to install: https://ailaflow.com/docs/how-to-install/
Show HN: AilaFlow – AI workflow automation for teams with Human-AI interfaces
Show HN: Add AI Features to Your Front-End in Minutes – FrontLLM
Show HN: FrontLLM – request LLM directly from your front-end code
Qwen3 30B A3B Hits 13 token/s on 4xRaspberry Pi 5
Create Flow Builder with Multiple Triggers
Sequential Workflow Designer: Now with a Refreshed Template
You Don't Need Your Own Back End to Call LLM from Front End
Run Llama 3.3 70B Q40 on $1516 GPU 3.3 tok/s
Re:Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5, 6.43 tok/s (eval ...
on Saturday February 15, 2025 @08:17PM (#43064338)
I checked how it performs in long run (prediction) on 4 x Raspberry Pi 5:
* pos=0 => P 138 ms S 864 kB R 1191 kB Connect
* pos=2000 => P 215 ms S 864 kB R 1191 kB .
* pos=4000 => P 256 ms S 864 kB R 1191 kB manager
* pos=6000 => P 335 ms S 864 kB R 1191 kB the
Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5, 6.43 tok/s (eval 11.68 tok/s)
Html2llm – Detect Elements on Webpage for LLMs, OmniParser WebAssembly
VisioPilot: Free AI Browser Automation Tool with Local LLM Server
Cursor-like programming on CodePen.io [video]
How to Run Llama 3 405B on Home Devices? Build AI Cluster
Llama 3.1 is available for home AI clusters! Run 8B model with the full context
Re:Run Llama 3 405B on home cluster (Distributed Llama)
on Tuesday July 23, 2024 @06:34AM (#41044566)
Technically, should be enought 2 machines with 128 GB RAM or 4 machines with 64 GB RAM (Q40 weights).
Run Llama 3 405B on home cluster (Distributed Llama)
Distributed Grok-1 (314B)
Show HN: Distributed Llama – Run LLMs on multiple devices in parallel
Re:Show HN: New visual language for teaching kids to code
on Tuesday November 21, 2023 @04:20PM (#38370357)
For example https://github.com/nocode-js/sequential-workflow-designer is designed in this way, that you program some logic by setting predefined actions in a proper order. You program at the high level.