neural-visualize — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited neural-visualize (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Generate the interactive knowledge graph dashboard and open it in your browser.
dashboard.html from the current indexhttp://localhost:7891Via MCP tool (neural-memory configured as MCP server in Claude Code):
Tool: neural_serve
{ "port": 7891, "open_browser": true }Via Python (working directly in the project):
import asyncio
from neural_memory.server import neural_serve, ServeInput
asyncio.run(neural_serve(ServeInput(port=7891, open_browser=True)))Windows: runpython -X utf8(or setPYTHONUTF8=1) to avoid cp1252 encoding errors from Unicode output.
Same-process requirement:neural_servestarts the HTTP server in a background thread within the running Python process. Stopping it requires callingneural_stop_serve(StopServeInput())in the same process before exit — not from a separate script invocation.
Standalone server (recommended for direct CLI use):
neural-memory-viz
neural-memory-viz --port 8080
neural-memory-viz --no-browser| Parameter | Type | Default | Description |
|---|---|---|---|
project_root | str | "." | Project root directory |
port | int | 7891 | HTTP port (change if 7891 is taken) |
open_browser | bool | true | Auto-open dashboard in browser |
regenerate | bool | true | Regenerate HTML from current index |
Run /neural-stop or call neural_stop_serve(StopServeInput()) in the same process.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.