Arakiss

Nahuali is governed, tamper-evident memory for AI agents. Load this skill whenever a task depends on context from earlier turns or sessions: recall before you answer (never assume), record what happened as it happens, assert durable facts only with evidence, and read the trust verdict on what you recall before you act on it. Unlike plain vector memory, every recall result comes back with a trust decision (CERTIFY / ADVISORY / WARN / BLOCK) and the evidence behind it, and the history is an append-only, hash-chained ledger you can audit. Trigger phrases: "remember this", "what do we know about", "recall", "check memory", "is this trustworthy", "what's missing", "was the history altered", or any task that leans on prior context. The command is `nahuali` (a single Rust binary); the same operations are exposed over MCP for hosts without shell access.

Install, configure, verify, troubleshoot, or operate the Gommage policy decision and audit harness for AI coding agents. Use when an agent is asked to set up Gommage, wire Claude Code or Codex hooks, install or manage the daemon, diagnose `gommage doctor` output, reason about Gommage policies/capability mappers/pictos/audit logs, evaluate release artifacts, or answer whether crates.io installation is supported.

Operate Slod, the local-first trace recorder and inspector for AI agent workflows.