Earlier this year we shipped verified TLS/HTTPS support in CMSDK, with a network_https test performing a real handshake and encrypted round-trips over loopback using a runtime-generated certificate. That proved the transport worked. It did not, on its own, make it safe by default — and we said at the time that certificate-verification hardening was on…
Almost every real-time pipeline eventually needs to wait for a combination of things. Fuse three sensors before you act. Wait until both the transcript and the speaker ID have landed. Proceed once any two of five nodes report ready. Classic publish/subscribe gives you one trigger per message, so that logic has always ended up inside…
Real-time systems are rarely pure. Alongside your in-process Psyclone modules there is almost always a helper that has to live in its own process — a vendor SDK that insists on owning main(), a Python service, a camera daemon, a licensed binary you cannot link against. Until now, wiring those into a Psyclone node meant…
A rigorous single-node latency benchmark of Psyclone AIOS against NATS, ROS 2, iceoryx, eCAL and ZeroMQ – competitive default speed, the tightest tails measured, and the runtime-reconfiguration capabilities that set it apart.
Psyclone modules can now drive Amazon Bedrock and Google Gemini directly — bringing native, low-latency generative-AI inference into the real-time pub/sub fabric for building sub-second AI applications.
The SSL build now links OpenSSL 3 and ships a network_https unit test that performs a real TLS handshake and encrypted HTTP round-trips over loopback with a runtime-generated certificate — with a clear certificate-verification hardening path on the roadmap.
The psytest suite was rebuilt into a context-chained set of stages exercising context switching, time sync, guaranteed & best-effort messaging, signals, and catalog retrieval — each stage emitting a PASS/FAIL + perf line with a final aggregated verdict. It now reports full p50/p90/p95/p99/p99.9 tail-latency percentiles, not just averages.
A ground-up CMSDK test framework: one PASS/FAIL line per object, per-test process isolation with timeouts (a crash in one test can’t take down the suite), self-healing shared-memory cleanup, and timestamped performance JSON with %-deltas for automated regression detection. 33 tests, all passing.
The message-routing fast path was rebuilt: a 36KB per-message ring copy replaced with a circular write index, a per-message heap allocation and no-match leak removed from routing, header receive reduced to a single allocation, and six redundant syscalls stripped from every send/read cycle.
The same socket-mode and buffered-read optimisations lifted best-effort UDP messaging to 155,000 messages/second (up from ~107k) with latency down to about 6 microseconds (from 9.3us) — reinforcing Psyclone’s sub-10us real-time profile.