Documentation
Understand the system before you give it work.
A concise, static guide to installation, model runtimes, context, the SI Agent, reviewed edits, remote GPUs, security boundaries and recovery.
Getting started
Install, diagnose, choose a model and run the first safe task.
02Models & providers
Local Ollama, SSH-tunneled remote Ollama and explicit OpenAI-compatible endpoints.
03SI Agent
Ask, Plan and Agent modes, permissions, tools and verification.
04Context & memory
Workspace indexing, attachments, context budgets and local lexical chat memory.
05Editing & verification
Proposal review, atomic edits, undo, tests and bounded repair.
06Remote GPU
SSH setup, host-key trust, remote Ollama discovery and telemetry.
07Security model
Workspace scope, approvals, sensitive operations and what is not sandboxed.
08Troubleshooting
Model discovery, remote disconnects, package mismatch and stalled tasks.
09Architecture
Core, providers, context, agent, editing, terminal, remote and UI layers.
TuxNest hybrid compute
Your GPU. Your AI. Your Control. Anywhere.
TuxNest connects a reviewable VS Code coding workflow with selected local models, SSH-tunneled models on user-controlled GPU workstations and explicitly configured compatible endpoints.