Provides a personal-agent skill for Hermes agents that evaluates ocular microsaccade rate, main-sequence velocity kinetics, and fixational drift to produce alertness/fatigue scores and classifications, enabling vigilance monitoring and intervention.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Zero-dependency sovereign personal agent skill for evaluating ocular fixational microsaccade rate (Hz), main sequence velocity kinetics, involuntary ocular drift, and mental vigilance fatigue.
flowchart TD
GazeFixation["High-Resolution Visual Fixation Stream"] --> DetectMS["Microsaccade Detection (Amp 0.1-0.8 deg)"]
DetectMS --> RateCalc["Microsaccade Rate (Hz = Count / Sec)"]
DetectMS --> MainSeq["Main Sequence Ratio (Q = Vmax / Amp)"]
GazeFixation --> DriftCalc["Involuntary Inter-Saccadic Slow Drift Velocity"]
RateCalc & MainSeq & DriftCalc --> VigilanceEngine["Cognitive Alertness & Ocular Fatigue Engine"]
VigilanceEngine --> Agent["OpenClaw / Hermes Personal Agent Intervention"]Deterministic Math: Pure Python standard library implementation with zero external dependencies.
Ocular Kinematics Standards: Implements validated equations for fixational microsaccade frequency, main sequence velocity scaling, and ocular drift velocity.
Mental Fatigue & Drowsiness Screening: Sensitive detection of central vigilance drops and microsleep risks during prolonged cognitive effort.
Model Context Protocol (MCP): Native JSON-RPC tool integration for LLMs and autonomous agents.
Related MCP server: ocular-tear-film
from client import OcularMicrosaccadeRateClient
client = OcularMicrosaccadeRateClient()
result = client.evaluate_microsaccade_dynamics(
fixation_duration_sec=30.0,
microsaccade_count=54,
mean_amplitude_deg=0.35,
mean_peak_velocity_deg_s=15.2,
mean_drift_velocity_deg_s=0.32
)
print("Microsaccade Rate:", result["microsaccade_rate_hz"], "Hz")
print("Alertness Score:", result["fixational_alertness_score"])
print("Classification:", result["classification"])Apache-2.0
This server cannot be deployed
Fuses biometric signals into a stress score (0-100) for AI adaptation. MCP + A2A native.
Deterministic eligibility scoring for AI agents: CLEAR/HOLD/FAIL verdicts, published weights.
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
Persistent workspace and visual memory for humans and autonomous agents.
