From signal path to recovery path.
- WebRTC, LiveKit, audio/VAD/STT/LLM/TTS pipelines
- Typed tools, queues, cancellation, and degraded modes
- Memory retrieval, provenance, policy, and compaction
- OpenTelemetry, traces, metrics, and operator surfaces
Mert Sefa Akgün
I design and ship real-time AI agents, voice systems, memory infrastructure, and the observable runtimes underneath them.
Three proof lanes show the current specialization, the architecture thesis behind it, and the lower-level systems roots underneath both.
NDA-safe architecture from production work
A production-oriented LiveKit pipeline spanning audio ingress, VAD, STT, LLM/tool mediation, TTS, interruption recovery, memory side paths, and stage-level telemetry.
Personal agent infrastructure
A typed memory policy where source, trust, sensitivity, allowed use, expiry, and auditability stay attached to retrieval instead of disappearing into embeddings.
Embedded/RF systems roots
A field-system design combining UWB ranging, Bluetooth provisioning, and GPS/time sync under access-control hardware constraints.
Architecture notes expose constraints, owner boundaries, failure modes, and trade-offs. Older systems material stays available as evidence of the path, not nostalgia.
An NDA-safe field note on where voice-agent latency accumulates, which stage owns each delay, and why interruption recovery belongs in the budget.
Why source, trust, sensitivity, allowed use, expiry, and audit gates must remain first-class in an agent memory system.
A compact C++ systems note preserved from the old wiki: why global object initialization order leaks across translation units.
Memory placement as a maker primitive: ownership, lifetime, and why runtime shape matters for C, C++, and Rust.
From the old blog: UWB ranging, local Bluetooth configuration, GPS for outdoor/time sync, and real access-control hardware constraints.
A cleaned-up cryptography primer: define the terms, keep the threat model visible, avoid ceremony.
A preserved algorithm/wiki reference from the old site: universal integer coding using Fibonacci numbers as a compact representation exercise.
A tiny old wiki entry promoted into a craft note: editor variants, workflows, and the personal-tooling lineage behind the site.
Design notes for making autonomous tools feel inspectable: command logs, approval moments, abort buttons, and resumable context.
My work moves from audio frames and constrained devices to agent orchestration, retrieval policy, telemetry, and production operations. I care about explicit ownership, bounded failure modes, and evidence that survives the demo.
I am interested in real-time AI, voice systems, agent infrastructure, memory, observability, and architecture work where the runtime matters as much as the model.