Skip to content
André Borchert edited this page Jun 13, 2026 · 15 revisions

OSAI Wiki

Purpose

This wiki is the canonical detailed design and implementation guide for OSAI. The main repository README.md is the short entry point; the wiki holds the architecture, platform plans, benchmarking strategy, roadmap, and Codex build tasks.

OSAI is a design-stage server-only operating system for CPU-only AI app agents. It targets applications that embed local AI agents capable of understanding their own source code, accepting human instructions, generating patches, rebuilding, testing, syncing with Git, and improving the running application.

Current QEMU Bring-Up Status

The main repository currently boots an AArch64 QEMU-on-macOS prototype with UEFI handoff, serial logging, controlled exception diagnostics, generic timer discovery, GIC discovery, PSCI SMP bring-up for four CPUs, VirtIO-MMIO block and network smoke tests, a read-only initramfs lookup path, an EL0 /init syscall path, a kernel heap, a minimal control-plane supervisor, AI Cell lifecycle and core-lease enforcement metadata, shared model arena metadata, PMM/VMM checks, and boot telemetry.

Target Benefits

These are design targets until measured against tuned Linux/BSD baselines.

Area Target
TCP/UDP latency Up to 10-45% lower latency
Effective CPU-AI memory bandwidth 3-18% higher
Sustained usable CPU-core performance 2-12% higher
Scheduler jitter/migration Near-zero on hot AI paths

OSAI cannot exceed physical silicon limits. The expected gains come from reducing scheduler migration, context switching, page faults after warmup, generic network overhead, memory duplication, bad NUMA placement, and unrelated interrupts.

Implementation Order

  1. QEMU on macOS
  2. Intel Desktop Port
  3. Intel Xeon Port
  4. ARM/NVIDIA Port

Start Here

Architecture Pages

Platform Pages

Reference Pages

Clone this wiki locally