Agent systems · Edge infrastructure
Hermes
Multi-model orchestration with consensus, telemetry and recovery on mobile hardware.
The problem
An autonomous system needs more than a model response: it needs a way to weigh disagreement, handle unavailable providers, and inspect decisions after they fail.
What I built
The documented Hermes setup runs on a Samsung Galaxy A54 using Termux/Linux. A “Parliament of Minds” routes multiple LLM models through a consensus process for XAUUSD signal experiments. Separate serve and gateway processes, a cron watchdog, telemetry, and causal post-mortems support operation and review.
Constraints & lessons
Mobile hardware and external model availability constrain reliability. Consensus does not guarantee correctness. The original portfolio records a strategy refit pause from 22 September 2026; current operational status belongs to the telemetry console.
Result & evidence
The result is a documented multi-model orchestration experiment with observable operations and recovery mechanisms. Historical trading figures on the previous site have not been independently verified and are not presented as evidence of real-world investment performance. The contribution to 500-AI-Agents-Projects is PR #167: open and unmerged when checked on 6 October 2026; that is a historical check, not a current status assertion.