sk_repl_idle()'s messaging pump (repl.c) walked the entire live-VM registry every idle beat (~1Hz) and dispatched a full VM-EXEC "MSG-TICK" -- a dictionary lookup plus a 32-slot arena scan -- into every live VM, every tick, unconditionally, forever. Fine at Tripod's original 3-VM scale; a full 9-identity turn-attractor campaign exposed it as a genuine wall on riscv64 specifically (its TCG makes each dispatch cost more): the same campaign that completed in 194s/ 339s on amd64/aarch64 never finished on riscv64 at 9 VMs across three attempts, while 8 VMs there was fine in 159s. Ruled out capacity explanations before touching anything: bumping riscv64's QEMU RAM 1024->4096 changed nothing (reverted), and a live STADIUM-RES@/MSG-STATUS probe with all 9 VMs attached showed no depletion. Host memory pressure was also ruled out directly (one background task did get OOM-killed once during the investigation, but the identical stall reproduced again with 9.2GB free). The real mistake was three premature kills under 4 minutes with no way to tell "slow" from "stuck" from outside the guest -- fixed by having run_doe_batch.sh sample the qemu process's own /proc/<pid>/stat utime every 60s; with that signal, riscv64 at 9 VMs was unambiguously alive (climbing utime, no hang), just disproportionately slow going from 8 VMs (159s) to 9 (600s+ and climbing). This was never really a riscv64-only bug: an O(N) per-second walk over the full VM population doesn't scale to the hundreds of VMs this fleet is headed toward, on any architecture -- riscv64 just made it visible first, at N=9, because its per-dispatch cost is highest. Fixed by round-robin batching: the pump now dispatches to at most SK_MSG_PUMP_BATCH (4) live VMs per idle beat via a persistent cursor that resumes where the previous beat left off, instead of all of them every time. Bounds both the scan and dispatch cost to O(K) regardless of total VM count; any single VM's queue now drains roughly every ceil(N/K) beats instead of every beat, still bounded and still matching the pump's own existing best-effort contract. No new C primitives, no messaging/Stadium changes. Verified: clean build on all 3 architectures, then the full 3x9x3 campaign re-run on all 3 (not just riscv64) per the standing rule that a defect repair requires a clean re-run everywhere before anything counts as closed: amd64 198s 0 faults 99/99 tokens x8 656/656 K-conserved aarch64 339s 0 faults 99/99 tokens x8 659/659 K-conserved riscv64 178s 0 faults 99/99 tokens x8 659/659 K-conserved riscv64 went from "never completes" to faster than aarch64, same campaign, same seed, same identity set. No regression on amd64/ aarch64. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EXieurDfDSsDFdnSyusuWo
LithosAnanke v2.0.1
UEFI-bootable FORTH microkernel. Boots from firmware, initialises memory and interrupts, then runs the StarForth VM as its sole userspace runtime. No libc. No OS. Just stone and necessity.
Lithos (foundation) + Ananke (necessity) — the kernel under StarshipOS.
Status — M7.1 (Capsule System · Multi-VM Fleet)
| Milestone | Status | |
|---|---|---|
| M0–M6 | UEFI boot · PMM · VMM · IDT · APIC · heap · framebuffer VT100 console (v1.5.1-FINAL) | ✅ Complete |
| M7 | StarForth VM integration + parity validation | ✅ Complete |
| M7.1 | Capsule birth protocol · Mama FORTH vocabulary · Tripod multi-VM fleet (Hermes/Artemis) · Word-level ACL (Phases 1–7) | 🔄 In Progress |
| M8 | REPL — keyboard input, interactive Forth | Planned |
| M9 | Block storage — AHCI driver | Planned |
POST at boot: parity hash verified across amd64/aarch64/riscv64 · Mama capsule dictionary: 453 words
What's live in M7.1
- Tripod — a named multi-VM fleet (Hera the Mama VM, Artemis, two Hermes instances) births, runs, and re-births independently, verified booting live pre-REPL on all three architectures.
- Hermes — a 17-block inter-VM messaging/channel layer between fleet members, with async delivery and channel negotiation.
- Artemis — a Block Allocation Map (BAM) storage subsystem with Q48.16
block-heat tracking and cooldown/reclamation (
ART-COOL/ART-REAP). - Word-level ACL — every dictionary entry carries a TTL/allow/mode/pin
access-control record. Strict, TTL, and pinned modes; two console layers
(emergency
ok>and superuserzuse)ok>). Phases 1–7 complete (C infrastructure, FORTH policy layer,zusebootstrap superuser, Isabelle proof stubs, kernel parity); Phase 8 (Ed25519 PKI / thumbdrive challenge-response) is the only item remaining. Measured overhead once active on every check: +0.0054%–+0.0088%, CV = 0.000%, across a 3×3 Latin-square DoE campaign (architecture × seed × 30 replicates) — three orders of magnitude below the measurement floor. - VM Fleet Attractor physics — the L8 Jacquard mode selector now has a real per-VM heat channel into fleet-wide tuning, replacing hardcoded compudynamics constants with a dynamically-inferred rate.
- Kconfig build configuration — every physics/heartbeat/pipelining/ kernel-only tuning knob (~40 total) is now a discoverable, optional Kconfig symbol shared with the hosted VM build. See Quick Start below.
Quick Start
# Build kernel (requires cross-compilation toolchain, or native gcc)
make -f Makefile.starkernel ARCH=amd64
# Run in QEMU with OVMF
make -f Makefile.starkernel qemu
# Other architectures
make -f Makefile.starkernel ARCH=aarch64 qemu
make -f Makefile.starkernel ARCH=riscv64 qemu
Artifacts: build/amd64/kernel/starkernel_loader.efi · build/amd64/kernel/starkernel_kernel.elf
For the hosted VM by itself (Linux, no cross-compiler needed, no bare-metal tooling): see
the separate StarForth repository — LithosAnanke used to be a branch inside that repo,
now it's its own project with its own master.
Build configuration (optional)
Every kernel-only knob (STARFORTH_ENABLE_VM, PARITY_MODE, the shared
physics/heartbeat family, etc.) is an optional Kconfig symbol — a plain
make -f Makefile.starkernel uses the same defaults it always has unless
you opt in:
make -f Makefile.starkernel ARCH=amd64 menuconfig
make -f Makefile.starkernel ARCH=amd64 kernel_amd64_defconfig
Documentation
| System Architecture | Full kernel + VM design |
| HAL Reference | Hardware abstraction layer interfaces |
| Capsule System — M7.1 | Capsule birth protocol design |
| VM Fleet Attractor design log | Tripod/Hermes/Artemis physics + build-system history |
| Getting Started / Kconfig reference | Full symbol reference for both build targets |
| Changelog | Milestone-level history |
| Roadmap | Milestone plan through self-hosting |
License
Starship License 1.0 (SL-1.0) — free for personal, research, and educational use. Commercial use requires a separate agreement. Attribution to R.A. James (Captain Bob) must be preserved in all distributions.
Patent pending. USPTO provisional filed December 2025 — physics-grounded self-adaptive runtime system. This license does not grant patent rights. Licensing inquiries: rajames440@gmail.com
Robert A. James (Captain Bob) · Systems Engineer · Hacking since 1973