URGE Universal Reasoning Governance Engine  ·  v0.1.1  ·  Rust  ·  Apache-2.0

LLM agents can act, but they cannot prove why an action was allowed. URGE is a deterministic governance gate: wrap any agent action in a formal policy check and get back an auditable verdict with a full reasoning trace.

▶ Try the live demo Runs entirely in your browser. No install, no sign-up.

Then add it to a project: cargo add urge Apache-2.0 · seven crates on crates.io

What you get back

A verdict — permitted or denied — with a confidence score, the formal notation the decision was expressed in, and citations for every step that produced it. The same policy evaluated twice gives the same answer, which is the point: a governance decision you cannot reproduce is not a governance decision.

Logic paradigms

ParadigmOperatorsGovernance role
Boolean∧ ∨ ¬ → ↔ ⊕Base layer, all systems
Modal (S5)□ ◇Access across system states
EpistemicK B CAgent knowledge verification
DeonticO P FObligations and permissions
Temporal (LTL)G F X UDeadline enforcement
Fuzzyμ ⊓ ⊔Thresholds and uncertainty
ParaconsistentBelnap 4-valuedContradiction without explosion
ProbabilisticP(·)Bayesian confidence — planned, not implemented

Seven are implemented and cross-validated against each other. The eighth is on the roadmap and is listed here so the table is not read as a promise.

Read on