Memories & Review Inbox

import { Tabs, TabItem } from ‘@astrojs/starlight/components’;

Kiomon is memory-native: instead of agents scribbling notes into a flat store, every piece of agent-authored knowledge is a memory with a type, metadata, and a lifecycle. This page covers the whole stack.

The four memory kinds

Memories are typed so they can be searched, filtered, and used appropriately:

Kind	Code	Friendly name	What it captures	Save framing
Files	reference	Files	Imported saved content (reference = imported content)	Keep this
Facts	semantic	Facts	Knowledge, facts, relationships between entities	Teach it
Routines	procedural	Routines	How-to rules, steps, triggers, preferences	Automate it
Moments	episodic	Moments	Events with an occurred_at timestamp	Log it

Each memory carries:

• title — short, searchable heading
• excerpt — the one-line card subheading (shown under the title everywhere)
• body — the full content
• tags — up to 20
• confidence — 0–1, an estimate of how reliable the memory is
• entities / claims / domain — structured metadata that makes memory searchable and consolidatable. Supplying these at write time skips Kiomon’s paid extraction pass.
• source_refs — IDs of the documents/memories the memory was derived from (wired into derived_from graph edges on approval)

The review-inbox flow

Everything an agent writes goes through review — nothing is active until approved:

Agent writes (draft_memory / reflect_session)
        │
        ▼
   pending_approval draft  ──►  Dashboard Review Inbox
        │                          │
        │ approve                  │ approve (via API/MCP too)
        ▼                          ▼
   ACTIVE memory            ACTIVE memory
   (searchable, embedded,   + derived_from edges wired
    graphed, retrievable)

Key rules:

• Drafts are excluded from search, listing, and RAG by default
• Drafts are never added to semantic search
• Approving promotes the draft to an active memory that participates in everything, including the derived_from edges for its source_refs
• Rejecting archives the draft
• Pending drafts that sit in the inbox too long are cleaned up automatically

You approve/reject from the dashboard Review Inbox page, or remotely via the MCP manage_memory tool (action: "approve" | "reject").

Lifecycle controls

Control	Tool / API	Effect
Pin	manage_memory → pin	Exempt from decay; always ranks at the top of retrieval
Unpin	manage_memory → unpin	Returns to normal strength dynamics
Archive	manage_memory → archive	Soft-hide from retrieval; recoverable
Restore	manage_memory → restore	Un-archive
Forget	manage_memory → forget	Permanent purge (from stores, index, vectors, graph)
Rate	manage_memory → rate (+1/-1)	Feedback feeds strength signals
TTL	(episodic)	Episodic memories have a time-to-live; old moments expire when their TTL passes

Strength, confidence, and decay

Memories aren’t static blobs — they have a health model:

• Strength — rises with retrieval and positive ratings. Pinned memories are strong by construction.
• Confidence — the memory’s self-assessed reliability (0–1). Contradictions halve confidence: if a new memory contradicts an existing one, the older memory’s confidence drops by half, surfacing the tension.
• Decay — unpinned memories slowly lose strength over time unless they’re retrieved or rated. This keeps your brain healthy: unused facts fade, used facts stay sharp.

Consolidation

A background process runs memory consolidation: related memories get promoted and linked, so fragments of knowledge merge into coherent clusters in the graph. Combined with automatic extraction of entities/claims/domain, consolidation is what stops your brain from degrading into a pile of unrelated notes.

Memories via API

• Write — POST /api/memories/batch-draft accepts 1–25 learnings per call (the MCP server uses this under the hood).
• Read — GET /api/memories lists memories (with kind filters); search via GET /api/search?kind=....

Memory vs. document

	Document	Memory
Who writes it	You (extension/connectors)	Agents + you
Content	Imported content (pages, files, notes)	Agent-authored knowledge
Types	source-based	reference / semantic / procedural / episodic
Approval	Immediate	Review Inbox for agent drafts
Lifecycle	archive/restore/forget	+ pin, decay, rating, confidence, contradiction, TTL
Graph	document links + suggestions	typed relations (derived_from, supports, contradicts, …)