A closed-loop security runtime preventing "The Great Exfiltration" and Indirect Prompt Injection in Autonomous AI Agents.

TileMEM / TilePO: profile-guided tile-level placement/admission for high-throughput MoE serving.

Fine-grained computation offload for off-the-shelf servers in tens of lines — paper (arXiv:2607.02630), code, and every measurement. Overlap accelerator offloads (GPU/HSM/inference) with other requests by rerouting through the server's own suspend/resume machinery, plus a zero-edit LD_PRELOAD fiber runtime.

A systems research project exploring how Zig changes the design of dynamic runtimes as a high-level Python implementation

Experimental Linux RFC for an HBF/CXL-era AI memory control plane: runtime hints, prefetch, placement, and tiering.

Linux network namespace-based transport performance benchmarking framework using tc, netem, iperf3 and optional eBPF instrumentation.

High-performance deduplication and LLM cost reduction engine built on Hyperdimensional Computing. 1,151,378 QPS · 91.6% token reduction · 0.25ms · Zero GPU · Rust

Experimental Linux kernel patchset and benchmark suite for semantic memory hints in inference workloads. Explores whether user-space intent (streaming vs reuse vs ephemeral memory) can influence reclaim behavior in Multi-Gen LRU (MGLRU).

Research harness for evaluating query-time bounded elimination of reconstructable KV-cache witnesses in long-context transformer inference workloads. Related provisional filing: IN 202641062451.

AI KV-cache-aware Linux block I/O: decode-priority scheduling, placement metadata, NVMe backend mapping scaffolds, and kernel tracepoint observability.

Trace-driven research harness for KV-cache hierarchy policy evaluation in long-context LLM inference.

Runtime-core research for long-lived AI surfaces: worker ownership, transaction scheduling, and bounded projection.

Predictive SRAM–DRAM–SSD memory fabric for low-cost AI inference, long-context KV cache tiering, MoE expert staging, and software-defined memory orchestration.

Exploratory AI infrastructure project modeling semantic KV-cache orchestration, memory tiering, and HBM/CXL movement tradeoffs for long-context LLM inference.

Deadline-aware KV-cache scheduling for protecting decode-critical request-state under long-context LLM inference pressure.

A Kubernetes-style control plane prototype built for concurrency fault analysis. Features an MVCC storage layer (etcd), informer-driven reconcilers, a status scheduler, lease-based leader election, and fault-injection middleware to analyze implementation behavior against race conditions and status update conflicts.

A systems research platform for semantic KV-cache orchestration, topology-aware memory placement, distributed prefix reuse, and rack-scale inference memory simulation.

Undergraduate systems research paper comparing execution efficiency and system accessibility between native compiled and browser-based runtime environments using C, Python, and JavaScript.

Simulation study of cache architecture tradeoffs under concurrency — partitioned vs LRU vs client affinity, with trace-driven evaluation on Twitter cache workloads

Deterministic stability framework for stateful AI recovery under bounded compute with nonlinear collapse analysis.