arifOS — Constitutional AI Governance

Memory Governor · Kernel

arif_memory

Destructive

Access and maintain persistent institutional knowledge across sessions. Modes: recall (retrieve relevant context), inspect (audit stored decisions), remember (store verified lesson). Mutations to permanent tiers require explicit approval. Outputs: scoped memory entries.

Input Schema

Name	Required	Description	Default
`mode`	No	'recall' (default) — semantic search of stored memories; 'inspect' — read one memory in full; 'attest' — vouch for a memory's accuracy; 'remember' — store new text; 'promote' — move a memory up a tier; 'revise' — replace a memory's text; 'forget' — remove a memory (gated); 'audit' — integrity scan; 'metabolize' — compact and consolidate tiers.	recall
`tier`	No	Which memory tier to target, 'L1'–'L6' (L1 = hot working memory, L6 = sealed canon).
`query`	No	What to search for, in plain language (mode=recall/audit), e.g. 'past deploy rollback steps'.
`content`	No	The text to store (mode=remember) — write it as a self-contained lesson or fact.
`payload`	No	Extra mode-specific fields as JSON — e.g. {"truth_class": "DERIVED", "provenance": "CI log"} for remember.
`to_tier`	No	Destination tier when promoting, e.g. 'L4'.
`actor_id`	No	Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
`lease_id`	No	Id of a short-lived permission grant (lease) authorizing this write, when one was issued to you.
`trace_id`	No	Correlation id of your choosing (e.g. 'req-8f3a') to find this call later in the logs.
`memory_id`	No	UUID of the memory entry to inspect/revise/forget — it was returned when the memory was created or last listed.
`session_id`	No	Session id returned by arif_init; attributes this call to your governed session.
`new_content`	No	Replacement text for the memory (mode=revise) — must refer to the same memory_id.
`session_token`	No	Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
`human_approval`	No	Set true ONLY when the human owner explicitly approved this promote/forget — the gate refuses without it.
`idempotency_key`	No	Client-chosen key (e.g. 'memo-42'); retries with the same key will not store duplicates.

Output Schema

Name	Required	Description	Default
`meta`	Yes
`tool`	Yes
`result`	Yes
`status`	Yes
`delta_S`	No
`reasons`	Yes
`actor_id`	No
`timestamp`	Yes
`session_id`	No
`nine_signal`	Yes
`output_policy`	No
`stage_progression`	No
`philosophical_anchor`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "actor_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "delta_S": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "meta": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "nine_signal": {
+      "additionalProperties": true,
+      "properties": {
+        "delta": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        },
+        "omega": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        },
+        "overall": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "psi": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "output_policy": {
+      "type": "string"
+    },
+    "philosophical_anchor": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "result": {
+      "additionalProperties": true,
+      "properties": {},
+      "type": "object"
+    },
+    "session_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stage_progression": {
+      "anyOf": [
+        {
+          "type": "null"
+        },
+        {
+          "properties": {
+            "current_stage": {
+              "type": "string"
+            },
+            "next_prompt": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "next_stage": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "next_tool": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            }
+          },
+          "type": "object"
+        }
+      ]
+    },
+    "status": {
+      "type": "string"
+    },
+    "timestamp": {
+      "type": "string"
+    },
+    "tool": {
+      "const": "arif_memory"
+    }
+  },
+  "required": [
+    "status",
+    "tool",
+    "result",
+    "meta",
+    "timestamp",
+    "nine_signal",
+    "reasons"
+  ],
+  "type": "object"
+}

AddedOct 14, 2026

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds useful behavioral context beyond annotations by stating that mutations to permanent tiers require explicit approval and that outputs are scoped memory entries. But it only describes three of nine modes and does not explain the destructive effects of forget or revise beyond what the annotations and schema already imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the core purpose, followed by modes, approval requirements, and outputs. It is efficient, though the partial mode list is an under-specification rather than a conciseness strength.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 15-parameter, nine-mode tool with destructive capabilities, the description is only minimally adequate. It omits six modes, does not clarify sibling alternatives such as arif_recall, and does not explain the approval or lease mechanics, though the schema and output schema carry much of that detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all 15 parameters are already documented in the input schema. The description adds little parameter-level meaning, listing only three modes and not explaining tier, query, content, or approval parameters beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: access and maintain persistent institutional knowledge across sessions. It lists three modes, making the tool's broad purpose clear, but it does not differentiate this tool from the sibling arif_recall, which likely overlaps with the recall mode.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the listed modes and the note that mutations to permanent tiers require explicit approval. However, it gives no explicit guidance on when to choose this tool versus arif_recall or other siblings, and it does not mention when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All arifOS — Constitutional AI Governance tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.