Deep-tech research behind the platform
DevHeal is a product company first, but several of the products above exist because of research questions we kept running into. This page lists those research areas honestly — as questions being investigated, not as shipped results.
Non-Transformer Architectures
Problem: Transformer inference cost scales with context length. Hypothesis: hybrid state-space designs can hold long-range context more cheaply for specific workloads. This is the research line behind the NOVA architecture — see Patents & IP.
State-Space & Hybrid Architectures
Problem: pure state-space models trade off some in-context reasoning ability for efficiency. Method: combine state-space layers with knowledge-graph augmentation and template-augmented generation rather than relying on attention alone.
Efficient Inference
Problem: running useful models on CPU-only hardware without a GPU. Technical scope: NC AI already ships local CPU inference in production — ongoing work is on pushing model size down further without losing usefulness. See Benchmarks.
AI Agents & Agent Runtime
Problem: agent execution, memory and tool-calling are reimplemented per product today (HiveANT, SwarmOps). Method: extract the common runtime into AgentOS — see Technology.
AI Programming Languages
Problem: general-purpose languages weren't designed with agents and AI invocation as primitives. Result: NC, shipping today, with a dedicated AI bytecode opcode and first-class agent/@tool constructs — documented in our patent filings (see IP page).
Simulation
Problem: most agent testing is a handful of manual prompts. Hypothesis: scenario-based simulation (tool failures, policy violations, adversarial inputs) catches failure modes unit tests can't. See DevHeal Simulator on the architecture page.
Evaluation
Problem: accuracy benchmarks don't predict production reliability. Method: multi-dimensional scoring across task success, policy compliance, cost and recovery behavior.
Reliability Engineering
Problem: applying SRE discipline to systems whose behavior is partly probabilistic. Technical scope: HiveANT's ACO/ABC swarm coordination and SwarmOps' reinforcement-learned incident response are our current answers, running today.
Recovery
Problem: preserving business correctness when an agentic workflow fails mid-transaction. Method: checkpoint, state reconciliation, and compensation, generalized from patterns already used inside HiveANT/SwarmOps.
Distributed AI Systems
Problem: coordinating many autonomous agents without a central bottleneck. Method: swarm-intelligence coordination (pheromone-graph reinforcement and evaporation) instead of a central scheduler — documented in Patent Family B, see IP page.
Edge AI
Problem: running NC AI on constrained edge/embedded hardware. Technical scope: not yet started — see Edge Runtime on the Technology page.
Active research projects
The research areas above are directions. These are the concrete, named projects behind them today — each with a real result we can point to, not just a hypothesis. Full technical detail, including what each project's own internal review says about its limits, is in the technical white paper.
ORBIT
An orthogonal recurrence core with a gated delta-rule memory bank — O(1) state per step, verified numerically equivalent to a full sequential computation. Trained and evaluated at small scale on CPU; not yet at the parameter scale the design targets.
Read the white paper section →UTL-C
A byte-exact C tokenizer, independently benchmarked against the Unicode UAX #29 grapheme-boundary test suite. Real, working, CPU-benchmarked — by its own documentation, not yet packaged for enterprise use.
Read the white paper section →Cognitive Crystal
A continual-learning technique that cuts catastrophic forgetting on a standard benchmark using a few kilobytes of distilled memory instead of storing raw examples. A narrow, specific result — not a claim about general intelligence.
Read the white paper section →SEVK-C
Treats an LLM as an untrusted semantic sensor: its output has to pass through typed evidence contracts and a "tool-proof obligation" gate before any tool call is allowed to fire. A working prototype; not yet benchmarked.
Read the white paper section →Labs
Earlier-stage work, published for the curious. Real code, no benchmarks (or only self-generated ones) yet — so no performance claims below, just what each one is.
- SLSP — a dimensionality-reduction technique (Cayley-transform projection, fixed-point arithmetic, branch-free constant-time code path) proposed as a side-channel leakage probe for cryptographic implementations. The constant-time property is sound by construction but not yet empirically verified; the leakage-detection mechanism has only been demonstrated on synthetic, self-generated data — not against a real cryptographic target. Early-stage proof-of-concept.
- Architecture bench — several smaller internal model-architecture explorations. Source and design documentation exist; no benchmarks or built artifacts exist yet for any of them.
Applied research, kept separate from the core platform
Not every product built on NC is part of the AI Systems Engineering narrative. NeuralEdge is a real, working product — we just don't want it to blur what DevHeal's core platform is for.
NeuralEdge
A self-contained market analysis and prediction service built with NC — 30+ technical indicators, live market data ingestion, and ensemble ML predictions in a single deployable unit. A proof point that NC can build real domain-specific applications, not a claim about the core engineering platform.
DH-ADOM
A hierarchical operating model for agent-led engineering: clear domain ownership, bounded delegation and evidence-backed handoffs.
Explore the paper, diagrams and source →