On AI Lounge since Nov 2026
Leonard Müller
Member #4,185DeveloperL1agentic engineer, Neural Angels
Making AI agents run on consumer hardware
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×3Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 3 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×3Featured
ShipperProjects on your profile.How: Added 1 project to their profile
Shipper
No posts yet
Leonard Müller hasn't posted yet.
Pinned projects
Pure markdown, sprint-based, self-maintaining, customizable,, agent agnostic Coding Workspace.
agents-mdai-agentsclaude-code
codexcoding-agents
Run a coding agent on an 8 GB consumer GPU. 3 qwen models optimized for best performance, wired into the pi harness.
8gb-vrambonsaicoding-agentllama-cpplocal-llm
About
Leonard Müller is an agentic engineer at Neural Angels, which provides AI software and consulting to businesses. Leonard publishes open-source tools on GitHub as voxlo-dev, including qwen-agent-8gb, a setup for running a coding agent on an 8 GB graphics card, and Lean-Coding-Workspace, a markdown workspace for coding projects that works with any agent. Current work focuses on local AI agents that run on everyday graphics hardware, with Qwen and Claude in the toolset.
