SYSTEMS · AI-NATIVE OS
A local-only, AI-native Linux distribution where you control the desktop by describing what you want instead of clicking through it.
↓ SCROLL
Every desktop OS still assumes you drive it by hand: hunting through menus, memorizing terminal flags, and repeating the same setup steps over and over. AI sits bolted on as a chat box in the corner, unable to actually touch the system. Rimuru starts from the opposite premise, that the AI is the interface. You boot the machine, say 'set up my development environment for Rust,' and the system parses the intent, plans the steps, and executes them across the terminal, GUI apps, and browser. The hard part is doing this reliably and privately, without shipping your screen to a cloud API.
Rimuru runs entirely on the local machine using quantized models served through Ollama, so nothing leaves the device. Natural language from voice or a search panel is routed through an orchestration layer that parses intent, plans a goal, and picks the right model for the job: a fast 3B model for reactions, an 8B for multi-step planning, a 14B for hard problems, and a vision model for reading the screen. To actually control applications it uses a four-tier fallback chain, always preferring the most reliable method available: native APIs first, then the accessibility tree, then pre-recorded OSWorld interaction patterns, and only as a last resort vision plus simulated input. Every autonomous action is gated by confidence, checkpointed for undo, and written to an append-only audit log.
You speak or type a request through a voice indicator or search panel, for example 'set up my Rust environment.'
The orchestration layer parses the intent, builds a goal plan, and routes each step to the right local model: reactive 3B, reasoning 8B, deep-planning 14B, or the LLaVA vision model for reading the screen.
Perception combines screen capture, OCR, YOLOv8 detection, and the AT-SPI2 accessibility tree to locate the exact elements to act on, using Set-of-Marks overlays so the vision model can point at numbered targets.
The executor tries the most reliable control method first: native API, then accessibility tree, then a recorded OSWorld pattern, then vision plus input simulation, acting across terminal, GUI, and browser.
Confidence-based execution runs low-risk tasks automatically, uses countdown timers for medium confidence, and asks for approval otherwise. A checkpoint is taken before every change so any action can be rolled back.
Every action lands in an append-only audit log, and recorded user trajectories let the system learn to replay tasks by semantic matching rather than pixel coordinates.
Drive the terminal, desktop apps, and browser by describing the outcome instead of performing each click.
All inference runs on-device through Ollama and llama.cpp, so no screen data or prompts leave the machine.
A fallback chain from native APIs down to vision plus input simulation keeps control working even when an app exposes no clean interface.
Demonstrate a task once and the system learns to repeat it, adapting the recorded pattern to environmental changes through semantic matching.
Checkpoints enable rollback of file, package, and config changes; sandbox mode previews what an action would do; an append-only log records everything the AI touches.
High-confidence, low-risk actions run on their own while riskier ones require a countdown or explicit approval.