Edge collector · Available now
The native macOS service observes supported processes, applications, extensions, model metadata, containers, and MCP configuration sources without arbitrary filesystem crawling.
Edge-first architecture
AxLoop begins where users and agents initiate work, preserves privacy-controlled evidence on the device, and provides the foundation for reconstructing supported AI interactions.
Talk to AxLoopAvailable now / passive evidence pipeline
AxLoop observes supported surfaces on the device, classifies evidence locally, and can export normalized inventory through OpenTelemetry. Correlation and tracing build on this foundation.
Privacy boundary No prompts, responses, source code, credentials, raw paths, or tool payloads.
axloop.asset.observedaxloop.device.inventoryThe native macOS service observes supported processes, applications, extensions, model metadata, containers, and MCP configuration sources without arbitrary filesystem crawling.
Classification, privacy controls, inventory state, and a durable delivery outbox remain on the device. Export is off by default.
Optional OTLP export sends normalized evidence to infrastructure you control, supporting fleet reconciliation without exporting prompts, source code, or tool payloads.
AxLoop is extending discovery evidence to correlate supported process, parent-process, connection, endpoint, agent, model, MCP, and timestamp relationships.
The platform direction is to reconstruct the observable sequence from agent to tool to application, then compare expected and observed outcomes.
Governance will build on trustworthy traces, with policy decisions, human approval, enforcement at supported control points, and a defensible event history.
AxLoop AI
Discover first. Correlate next. Never present inference as observation.