More tools ≠ more chaos. Liminal combines lazy families, resource locks, human approval, and an optional single-token safety judge so autonomy scales without reckless shell access.

Lazy tool families

On startup the model sees a baseline profile (balanced, knowledge_first, or max_autonomy). Everything else — git, browser, document engine, vault — loads via activate_tool_family.

Danger levels

LevelExamplesBehavior
Normalread_file, recallRuns when model calls
Destructiverun_shell, run_backgroundApproval unless YOLO / judge

Locks serialize access to paths and shell so parallel tool calls don't corrupt state.

Safety judge (optional)

AGENT_SAFETY_JUDGE=1 runs the fast model with a 0/1 verdict before showing you the approval modal. Cached briefly per (tool, args) — advisory only; when in doubt the harness still asks.

Critics and verification

Optional verify_result / critics run when answers are code-heavy — another fast-model pass before you trust a "done" message.

Feature listEvery major tool family on one page.

Try Liminal on your machine

Free, MIT licensed, one-command install. No account required.

— The Vireon Dynamics team