TuxNest · local-first AI engineering
Own the model. Own the workflow.
Local-first AI engineering for VS Code. TuxNest connects your editor to models you control—local Ollama, your own remote GPU over SSH, or explicit OpenAI-compatible endpoints—with reviewable edits and real verification.
Built around control.
Minimal interface, explicit model choice, reviewable changes and evidence you can inspect.
01Local by default
Run Ollama on your own machine and keep model execution close to your code.
02Remote when you choose
Connect to your own GPU host over an SSH tunnel without moving your workspace.
03Changes stay reviewable
Agent edits remain visible, reviewable and under your approval.
04Execution leaves evidence
Runs expose real reads, commands, output and validation instead of relying on claims.
Local AI should feel local.
Your editor, your model runtime, your hardware and your approval remain first-class parts of the workflow.