Yes. OpenShell and Trustabl address different layers. OpenShell helps isolate the runtime; Trustabl’s analyzer checks agent code and configuration for reliability and safety issues before deployment. Automated OpenShell policy generation is planned for Trustabl Console, not part of the open-source scanner today.
No. trustabl enrich shows proposed patches for review. It applies changes only when you run with --apply, and the resulting files remain under your normal version-control workflow. Review the diff before committing.
Yes. Trustabl is essentially a specialized linter for AI agents. While traditional linters (like ESLint or Ruff) focus on code style, syntax, and general bugs, Trustabl analyzes your AI agents, tools, prompts, and SDK configurations for reliability, safety, and production readiness — flagging patterns that expose you to prompt injection, missing timeouts, tool misconfigurations, and guardrail gaps that standard linters miss. Think of it as "ESLint for AI agents" — it runs in CI/CD, gives clear explanations and fix suggestions, and helps you ship safer, more robust agentic systems.
Trustabl is actively expanding scanner coverage, reliability rules, developer integrations, and governance workflows. Available today: local deterministic scanning across nine SDKs and seven languages, GitHub Actions, Claude Code, OpenAI Codex, Gemini CLI, VS Code, Cursor, and reviewed fixes through trustabl enrich. Trustabl Console is the planned commercial layer for policy generation, compliance mapping, and signed governance snapshots.
