NevoFlux

Security & Privacy

How NevoFlux handles your data, keys, and the agent's permissions.

Where your data lives

NevoFlux is local-first. Your sessions, knowledge base (~/.gbrain/), config, and API keys are stored on your own machine. The agent runs as a local process bundled with the browser.

What leaves your machine: the requests you send to your chosen LLM provider go to that provider, and any MCP servers or web tools you use reach their respective endpoints.

API keys

Keys live in config.toml or in environment variables — NevoFlux does not use an OS keychain. Treat config.toml as a secret file and avoid committing it anywhere.

The agent asks before it acts

By default the agent runs in Confirm before actions mode: it asks for your approval before running tools or commands. You can opt into Auto-execute in Settings → General — do so deliberately.

Tool and command safety

  • Canvas tools run through a whitelist: no shell, validated parameters, path confinement, output/time limits, and an audit log.
  • Command auto-approval is governed by the [auth] section of config.toml, including an allowlist and patterns for sensitive files.
  • Canvas artifacts run in a sandboxed iframe, and the bridge between page content and the browser is isolated.

Reporting a vulnerability

Please report security issues responsibly via the GitHub repository.

On this page