anthropomorphic-agent-engine@2.6.1
VERIFIEDPublisher claims: "Anthropomorphic psychology engine based on SPL Pure Core V8.0, modeling emotion, mood, memory, trauma, trust, self-esteem, sleep and expectation as continuous-state subsystems. The fully local core is deterministic and bit-exactly replayable under virtual-clock injection: no LLM, no RNG, no network. Adult-oriented capabilities sit behind a Step 0 age gate (18+) - the strict full-range core refuses event entry until confirmed, while a minor or declining answer routes to safe mode via the shipped minor-protection core; only the derived boolean is persisted, never a numeric age. Optional LLM adapters (OpenAI / Claude / Chain) are OFF by default, opt-in only, networked and non-deterministic; they render text from a state snapshot and are excluded from the guarantee. Ships a loopback-only HTTP service with local SQLite persistence, hash-chain audit, guardian-consent and crisis flows. Extension modules under assets/feature-guide/ are reference-only and NOT wired into the core." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.