PRE-ALPHA RESEARCH · APACHE-2.0

The systems language built for coding agents, and readable by humans.

Meaning in. Verified machine code out.

Source remains a clear human projection. Coding agents work against typed meaning, stable identity, bounded context, and revision-bound changes instead of rewriting text by guesswork.

semaprax://v0.2pre-alpha research
revision  sha256:<program-state>
query     app.main --depth 1
context   typed · bounded · stable-id
patch     expected_revision == current
verify    fail_closed
target    native | browser/wasm

What is Semaprax?

Semaprax is an experimental agent-native systems programming language built around a stable semantic program graph. Its v0.2 prototype lets coding agents query typed meaning, submit revision-bound semantic patches, and lower a verified subset to native executables and browser/Wasm packages.

// 01

One program, three working surfaces

Human source, agent-facing meaning, and machine output are derived from one versioned semantic state. Every arrow below is an evidence boundary, not a promise of universal language support.

  1. Human sourceReadable syntax remains the review and authorship surface.
  2. Semantic program graphStable IDs expose typed meaning, context, diagnostics, and patch targets.
  3. Verified outputAdmitted subsets lower deterministically to native or browser/Wasm artifacts.

Semaprax semantic program graph: Semaprax parses human-readable source into validated HIR and a versioned semantic graph. Agents request bounded context by stable ID, preview or submit a patch against an exact revision, and receive deterministic diagnostics or evidence before native or Wasm lowering.

// 02

The hypothesis, not the headline

Semaprax tests whether a programming system can reduce the context and repair ambiguity faced by coding agents. Lower model cost is a hypothesis. It is not yet supported by model-token, latency, answer-quality, or repository-scale evidence.

UNPROVEN HYPOTHESIS Less agent context and lower cost at repository scale
// 03

A research index with one owner per question

Each page answers one branded question so search engines and answer engines do not have to guess which route is authoritative.

// 04

Capability evidence ledger

Current statusEvidence stateScopeEvidence
Stable semantic program graphImplementedVersioned Graph v10-v14 JSON for the documented typed subset, with persistent identities and validated HIR shared by native and Wasm lowering.GitHub repository
Bounded agent contextImplementedAgent Context v1 plus additive v2 call traversal, with deterministic byte, node, depth, and frontier limits.GitHub repository
Revision-bound semantic patchesImplementedAtomic Patch v1 and bounded Patch v2 operations, with exact revision checks, stale rejection, and selective semantic delta validation.GitHub repository
Semantic review and evidence capsulesDemonstratedBounded review, impact, target, patch, and workspace evidence routes with deterministic artifacts and explicit nonclaims.GitHub repository
Native and browser/Wasm loweringDemonstratedDocumented scalar, control-flow, record, variant, generic, contract, and bounded ownership slices through C11/Clang and real Node/Wasm gates.GitHub repository
Ownership-inspired memory managementExperimentalExplicit own, borrow, and shared boundaries plus move checking and bounded resource cleanup protocols. This is not Rust compatibility or a complete borrow checker.GitHub repository
// FAQ

Questions, answered without the hype

Is Semaprax production-ready?

No. Semaprax is Apache-2.0 pre-alpha research. The repository calls itself an executable architectural seed, and the evidence ledger separates bounded implementation from general completion.

Is Semaprax only for AI agents?

No. The source projection is designed to stay readable by humans. Agent-native describes the stable semantic graph, bounded context, diagnostics, and patch interface available to coding agents.

Need this level of evidence-first engineering in your AI product?

See Wavect’s AI engineering work.
Created by Wavect as an open-source systems research project. GitHub repository. GitHub specifications are the normative source. This page is a dated research summary.