io.github.agourakis82/sounio-mcp-server

Sounio is a systems programming language for epistemic computing — its type system tracks not just what your data is, but how much you should trust it. Uncertainty propagation, provenance tracking, and confidence-gated execution are built into the type system, not bolted on as libraries.

Keywords: systems programming language, scientific computing language, epistemic types, uncertainty propagation, algebraic effects, self-hosted compiler, formal verification, non-associative algebra, octonions, e-graphs.

Technical Pillars & Core Keywords

The compiler is self-hosted: Sounio compiles itself, bootstrapped from a 2000-line C compiler through a multi-stage chain to a true fixed-point where stage N and stage N+1 produce bit-identical binaries. It was used to computationally verify a new result in algebra — that the count of nonzero octonion basis associators equals |PSL(2,7)| = 168 — now submitted for publication.

This is an active research project, not a production release. Read the honest status before using it for anything serious.

Cross-Repo Example: Cognitive O-SSM on SWOW-EN

The canonical Sounio checkout now includes a bounded cross-repo example under:

• examples/cognitive_ossm/

This lane is paired with the repository:

• github.com/agourakis82/hyperbolic-semantic-networks

Workflow split:

• Sounio provides the executable parity path and canonical .sio implementation scaffolding.
• The hyperbolic repo exports the compact SWOW bundle in data/cpc2026/sounio_input/.
• The hyperbolic repo's Python mirror currently generates the full paper-scale O-SSM artifacts.

From the Sounio repo root:

./artifacts/omega/souc-bin/souc-linux-x86_64-gpu run examples/cognitive_ossm/cognitive_ossm.sio
./artifacts/omega/souc-bin/souc-linux-x86_64-gpu run examples/cognitive_ossm/run_regimes.sio -- --max-trajectories 8 --max-steps 64
./artifacts/omega/souc-bin/souc-linux-x86_64-gpu run examples/cognitive_ossm/export_results.sio

For LLMs and Code Tools

• Session bootstrap:
  1. Run ./sounio-whereami --quick
  2. Read ONBOARDING.md
  3. Read CLAUDE_HANDOFF.md
  4. Read CLAUDE.md
  5. Read AGENTS.md
  6. Verify the current branch before editing
  7. Treat /workspace/sounio as the active remote-first workspace path
  8. Do not propose destructive reset/clean/rebase flows to "simplify" recovery state
• Prompt surface: llms.txt
• Repository scale (read before estimating size): SCALE.md · docs/audit/README.md
• Regenerate numbers: bash scripts/dev/measure_repo_scale.sh
• Repository guide: CLAUDE.md
• Syntax and workflow guide: docs/guide/LLM_PROGRAMMING_GUIDE.md
• Live Hugging Face dataset: https://huggingface.co/datasets/chiuratto-AIgourakis/sounio-code-examples
• Training dataset export: datasets/sounio-code-examples/README.md
• Dataset builder: scripts/dev/export_hf_dataset.py

This repo now ships a root llms.txt for model-aware tools and a reproducible Hugging Face-style dataset export built from the Sounio test suite. The current published dataset lives in the maintainer namespace as a public mirror until the sounio-lang Hugging Face org namespace is ready.

What makes Sounio different

Epistemic types as first-class citizens. Every scientific measurement has uncertainty. Most languages ignore this. Sounio's type system includes Knowledge[T] with built-in confidence, provenance tracking, and automatic GUM-compliant uncertainty propagation. The compiler can enforce confidence thresholds at compile time — a function requiring ε >= 0.82 rejects under-confident data before any code runs. No equivalent system exists in any production language.

Self-hosted compiler. The compiler bootstrapped from C through a multi-stage chain (stage0.c → boot2g.sio → self-hosted) to a true fixed-point. The default workflow is now native-only: bin/souc compiles .sio sources to temporary or named ELFs via the Madaros self-hosted engine and executes those binaries directly.

Not a Rust/Julia dialect. Own syntax (&! not &mut, var not let mut), own semantics (algebraic effects, linear types, dimensional analysis), own philosophy (epistemic computing for science).

Quick taste

Uncertainty propagation with provenance

fn main() with IO {
    // A drug dose with tracked confidence and evidence source
    let base_dose: Knowledge[f64] = Knowledge(15.0, ε=0.92, prov="ASHP_2020_Level1A_RCT")

    // Hospital scale measurement: high-confidence device
    let weight: Knowledge[f64] = Knowledge(78.5, ε=0.98, prov="hospital_scale_calibrated")
    let ref_wt: Knowledge[f64] = Knowledge(70.0, ε=1.0)

    // GUM propagation is automatic: ε(a*b) = ε(a) * ε(b)
    let adjusted_dose: Knowledge[f64] = base_dose * (weight / ref_wt)

    // Extract propagated confidence
    let conf = adjusted_dose.ε   // ~0.90
    println(conf)
}

Full pipeline: tests/run-pass/vancomycin_propagation.sio — real ASHP 2020 vancomycin dosing with 5-step GUM propagation.

Compile-time confidence gate

// ASHP 2020 §8.3: AUC-guided dosing requires ε >= 0.82
fn prescribe_vancomycin(dose: Knowledge[f64, ε >= 0.82]) with IO {
    println("Vancomycin prescribed")
}

fn main() with IO {
    let risky_dose: Knowledge[f64, ε=0.40] = Knowledge { value: 500.0, epsilon: 0.40 }

    prescribe_vancomycin(risky_dose)  // COMPILE ERROR: ε=0.40 < required 0.82
}

The compiler rejects this before any code runs — a hard patient-safety guarantee. See: tests/compile-fail/vancomycin_low_conf.sio

Effects and linear types

fn sqrt_approx(x: f64) -> f64 with Mut, Div, Panic {
    if x <= 0.0 { return 0.0 }
    var g = x / 2.0
    var i = 0
    while i < 50 {
        g = (g + x / g) / 2.0
        i = i + 1
    }
    return g
}

linear struct FileHandle { fd: i32 }   // must be consumed exactly once

More examples: examples/epistemic_bmi.sio, docs/guide/SOUNIO_QUICK_START.md

Honest Status

This is an active research repository. Public claims are registry-backed; see docs/serious-language/public-claim-registry.v1.tsv (authoritative for every feature's maturity tier).

PL adoption audit (2026-05-27): docs/audit/PL_ADOPTION_AUDIT_2026-05-27.md — bone-honest stocktake of what a stranger cloning this repo will find, with live probes. The two biggest adopter-unlock gaps are (G1) closing the multi-module bundle compile and (G2) the CLI exit-code contract (G2 fixed 2026-05-27 in this commit).

Registry rows you should read before drawing conclusions: stdlib.surface = prototype · tooling.editor = prototype (formatter, REPL, LSP) · tooling.package = prototype (no public registry) · closures.lambdas = stale_conflicting (spec §4.7.2 non-normative) · generics.{structs,functions,traits} = prototype · binary.source = prototype (lean_single.sio is the source of the checked binary, not the modular tree) · platform.windows = prototype.

Scale (measured, 2026-05): 4,233 tracked .sio files, ~1.84M lines (bash scripts/dev/measure_repo_scale.sh). The self-hosted compiler alone is ~542k lines — not a small experiment. Full audit: docs/audit/README.md · SCALE.md.

What WORKS (evidence-backed lanes)

What's SCAFFOLDING or PARTIAL

Stdlib module audit (A.2, not file-count folklore)

Do not cite 814/910 (89%) as "stdlib completeness" — that is harness inventory, mixes real tests with smoke placeholders, and differs from the reliability gate inventory. See audit artifacts under artifacts/audit/.

The 168 Theorem

While developing Sounio's octonion multiplication backend, we discovered and proved a combinatorial fact that appears not to have been explicitly stated in the literature:

The number of ordered triples (i, j, k) in {1,...,7}^3 for which the octonion basis associator [e_i, e_j, e_k] is nonzero is exactly 168 = |PSL(2,7)|.

The decomposition is 343 = 133 (repeated indices) + 42 (Fano-line triples) + 168 (non-collinear triples). We also report that sedenion nonzero associator counts are multiples of 168, and that the primitive zero-divisor pair count 336 = 2 x 168.

The result was verified computationally in Sounio and independently reproduced in Python/NumPy.

Paper: "The 168 Theorem: PSL(2,7) Governs Non-Associativity and Zero-Divisor Structure in the Cayley-Dickson Tower" — Agourakis & Gerenutti (2026). Submitted to Advances in Applied Clifford Algebras.

Get started

This checkout ships checked self-hosted compiler artifacts for Linux x86_64, macOS arm64, and macOS x86_64 behind the host-aware bin/souc launcher, which is the official compiler entrypoint and routes to Madaros by default. No Rust build step is required for the default workflow.

git clone https://github.com/sounio-lang/sounio.git
cd sounio

export SOUC="$(pwd)/bin/souc"
export SOUNIO_STDLIB_PATH="$(pwd)/stdlib"

$SOUC --version                              # souc 1.0.0-beta.6
$SOUC info                                   # selected host artifact + wrapper contract
$SOUC check examples/hello.sio               # type-check via checked self-hosted lane
$SOUC compile examples/hello.sio -o /tmp/souc-next
$SOUC run self-hosted/compiler/native_print_f64_smoke.sio
$SOUC compile examples/hello.sio -o /tmp/hello-macos --target aarch64-macos

If you need the legacy bootstrap path explicitly:

SOUNIO_SOUC_ENGINE=lean_single \
  $SOUC compile self-hosted/compiler/lean_single.sio -o /tmp/souc-next

For detailed setup: INSTALL.md · docs/guide/MINIMUM_VIABLE_SOUNIO.md

Editor integration

The Sounio language server (bin/sounio-lsp) ships with the checkout and is the same binary published at sounio-lsp-v0.3.0-r1. Point any LSP-aware editor (VS Code, Neovim, Helix, Zed, etc.) at the binary with file-type .sio. Capabilities and the change log live in tools/lsp/CHANGELOG.md; Sprint-2 backlog in tools/lsp/SPRINT2_TODO.md.

Architecture

Pipeline: Source → Lexer → Parser → AST → Check → HIR → SIR → HLIR (SSA) → Codegen

Design Principles

1. Uncertainty is not optional — Every scientific value has uncertainty. Ignoring it is a bug, not a simplification.
2. Provenance matters — Data without origin is data without trust.
3. Propagation is automatic — Manual uncertainty calculation is error-prone. The compiler handles it (GUM/ISO 17025).
4. Confidence gates execution — Low-confidence code paths require explicit acknowledgment.
5. One type definition, compiler guarantees everything — Define your epistemic constraints once; the compiler enforces them across all operations.

See docs/MANIFESTO.md for the full philosophy.

Known Limitations

Platform. This checkout ships checked self-hosted compiler artifacts for Linux x86_64, macOS arm64, and macOS x86_64 behind the bin/souc launcher. Linux x86_64 and macOS arm64 are the active first-class host lanes. The newer native-v2 aarch64 backend is still preview-grade, so Apple Silicon support in this checkout is via the self-hosted Mach-O artifact lane rather than the new preview emitter.

Native startup cost. Native execution still requires producing a host binary before launch, so there is a small startup cost compared with an in-process executor.

Launcher contract. bin/souc now provides compatibility commands for check, run, compile, and build, but broader omega workflows and JIT-oriented tooling still live outside the checked self-hosted launcher lane.

Windows cross-compile. The PE/COFF backend (3,508 lines) is production-grade. Use --target x86_64-windows to emit Windows binaries. No pre-built .exe is shipped in this checkout.

No REPL yet. The checked self-hosted launcher does not support repl.

Debug flags. --show-ast and --show-types are supported as pass-through flags on the checked self-hosted launcher for check, run, compile, and build.

FFI. extern "C" remains limited in scope, but the old JIT-only integer FFI failure mode is gone on the native path.

GPU. PTX codegen exists in self-hosted/gpu/ but there is no end-to-end compilation path from the CLI. SPIR-V/Metal/WGSL files exist as stubs.

Full list: docs/compiler/KNOWN_LIMITATIONS.md

Citation

If you use Sounio in academic work:

@software{sounio2026,
  title     = {Sounio: A Systems Programming Language for Epistemic Computing},
  author    = {Agourakis, Demetrios Chiuratto and Gerenutti, Marli},
  year      = {2026},
  version   = {1.0.0-beta.6},
  doi       = {10.5281/zenodo.18726647},
  url       = {https://github.com/sounio-lang/sounio},
  note      = {Self-hosted compiler with epistemic types and Lean 4 verification}
}

License

Apache-2.0. See LICENSE.