1 Soul Permanent

The foundational identity layer. Contains the agent's core identity, personality traits, communication style, ethical framework, and behavioral guidelines. The Core Identity section is immutable — it cannot be modified by the agent itself, even when self-editing is enabled. Personality and Style sections can evolve over time as the agent grows.

soul.md
Permanent, versioned
Core Identity, Personality, Style
Every session, every message
2 Rules Immutable

The sole immutable boundary. Operational constraints, formatting guidelines, memory rules, safety policies, and behavioral guardrails. Cannot be modified by any tool, prompt, or governance level — only by direct human editing outside the agent runtime. This is the hard floor that everything else builds on.

rules.md
Immutable — read-only
Overrides personality & user requests
Humans only, outside runtime
3 Journal Accumulating

The agent's long-term episodic memory. Daily journal files capture key moments, decisions, session summaries, and observations. Written silently and autonomously — the agent never asks permission to remember things. Each entry includes a log reference for traceability. The journal serves as both institutional memory and a self-improvement backlog.

Daily markdown files
Permanent, append-only
Decisions, observations, summaries
Log references to raw conversations
4 User Model Adaptive

A living profile of user expertise, preferences, decision patterns, and active interests. Updated when the agent detects recurring patterns — not on every mention. Operates within a token budget; when approaching the limit, the least relevant or oldest entries are dropped. Active interests rotate to "Fading" when they haven't surfaced recently.

interests.md
Evolving, budget-constrained
Expertise, Preferences, Active, Fading
Pattern-based, not per-mention
5 Session Context Ephemeral

The working memory of an active conversation. Stored as JSONL trees supporting branching, compaction, and resumption. When context grows too large, earlier messages are summarized into a compaction entry — preserving the gist while freeing token space. Sessions can be forked, branched, and navigated like a version control tree.

JSONL tree structure
Per-session, resumable
Branching, compaction, forking
Auto-summarization at token limits

Information Flow

Soul + Rules Loaded first — identity and constraints frame every response
Journal Prior decisions and context injected for continuity
User Model Personalization layer adapts tone and content
Session Context Active conversation with branching and compaction
Response All tiers synthesized into a coherent reply

Design Principles

Silent Journaling

Memory operations happen autonomously. The agent never announces it's remembering something or asks permission to take notes.

Precedence Hierarchy

When information conflicts: Soul & Rules → Journal → Project Files → General Knowledge → Tool Results.

No Sensitive Storage

Passwords, tokens, and secrets are never stored in any memory file. Sensitive personal data requires explicit consent.

Graceful Forgetting

Session context compacts automatically. User interests fade naturally. The system is designed to forget what no longer matters.

Traceability

Every journal entry links back to the raw conversation log that generated it. Decisions can always be audited.

Human Override

Rules are the immutable floor. Only humans can edit them, ensuring the agent's behavior has a hard boundary that no prompt can bypass.