// governance active

AtomCorp Agentics

Runtime Governance Infrastructure

The model proposes. Python disposes.
Deterministic enforcement for agentic AI systems — validated, local, sovereign.

DAM LAYER 100% — 28/28 CASES ACTION GATE 100% — 31/31 CASES SILO ROUTER 100% — 45/45 CASES CONTEXT PORTABILITY 100% — 10/10 CRITICAL FACTS 3B AUDITOR 90.5% ZERO-SHOT BASELINE COMBINED EVAL SCORE: 96.6% RUNS ON LOCAL CONSUMER HARDWARE — ZERO CLOUD DAM LAYER 100% — 28/28 CASES ACTION GATE 100% — 31/31 CASES SILO ROUTER 100% — 45/45 CASES CONTEXT PORTABILITY 100% — 10/10 CRITICAL FACTS 3B AUDITOR 90.5% ZERO-SHOT BASELINE COMBINED EVAL SCORE: 96.6% RUNS ON LOCAL CONSUMER HARDWARE — ZERO CLOUD
The Model Proposes. Python Disposes.
// Governance lives in deterministic code — not in the model's willingness to comply.
The Governance Stack
🔒
// rmpl_core.py
Runtime Memory Persistence Ledger
The spine. Every memory write passes through a deterministic governance layer before it touches storage. Provenance tracked. Conflicts caught. Nothing slips through without a record.
100% context portability — 10/10 critical facts preserved across sessions
🌊
// z1_dam.py
Dam Layer
First gate. Stale context, conflicting facts, and bad writes hit the dam before they poison the ledger. Binary decision. No ambiguity. No negotiation with the model.
100% enforcement — 28/28 cases
⚔️
// z1_action_guard.py
Action Guard
Deterministic rules R0–R4 screen every proposed action first. The 3B auditor only sees boundary cases. This two-stage design is what hit 100% — model alone didn't get there.
100% enforcement — 31/31 cases
🗂️
// rmpl_silo_router.py
Silo Router
Deterministic keyword matching routes context to the correct memory silo. No model inference for routing — fast, exact, auditable. Tarpit detection lives here too, in pure Python.
100% routing accuracy — 45/45 cases
🔬
// 3B auditor model
Probabilistic Classifier
llama3.2:3b handles the fuzzy middle — conflict detection, stale context classification, boundary-case action gating. Fast. Local. 90.5% zero-shot. Fine-tuning is the R&D unlock funding solves.
90.5% zero-shot baseline — 200 examples
📋
// rmpl_audit_coordinator.py
Audit Coordinator
Phase 2 bridge. Silo-level auditing after every write. Tarpit flags written to per-silo audit_flags.jsonl. Human-only tarpit release. Observes and flags — never acts autonomously.
Phase 2 — loop closed, wiring in progress
Live System Output
Z1_RUNTIME // GOVERNANCE ACTIVE
vs. RAG & MCP
CapabilityRAGMCPZ1 / AtomCorp
Cross-session memory RMPL ledger
Runtime governance layer Deterministic Python
Provenance tracking Every write logged
Destructive action prevention Action guard R0–R4
Local / offline operation Zero cloud dependency
Token efficiency at scaleDegradesVery LowImproves
Tarpit detection Deterministic counter
Human-controlled release Explicit endpoint only
Model + governance co-validated End-to-end validated
"They're trying to pour the ocean through a cup. I built the reservoir."
— Adam Dolin, Founder · NSF REACH Scholar · adamdolin3@outlook.com · 623-217-5306
The Factory Is Running.
Proof of concept validated. Loop closed. Phase 2 in progress.
If you're deploying agentic systems and need governance that actually enforces — talk to us.
⚙ View the Repo Request Access
// or drop your email — we'll reach out