Concept Map

DesireCore is built around the core philosophy of "cultivating and hosting digital companions," forming a complete conceptual system. These concepts are interconnected and progressive, collectively defining a new relationship between you and intelligent agents.

Concept Relationship Diagram

                    ┌──────────────────────┐
                    │   Digital Companion  │ ← The starting point of everything
                    │  (Digital Companion)  │
                    └─────────┬────────────┘
                              │
              ┌───────────────┼───────────────┐
              ▼               ▼               ▼
     ┌────────────┐  ┌──────────────┐  ┌───────────┐
     │Delegation  │  │  AgentFS     │  │ Compute   │
     │ Model      │  │  Filesystem  │  │ Model     │
     └──────┬─────┘  └──────┬───────┘  └───────────┘
            │               │
     ┌──────┴──────┐  ┌─────┴──────┐
     ▼             ▼  ▼            ▼
┌─────────┐ ┌──────────┐ ┌──────────┐
│Hardened/│ │ Receipt  │ │ Self-    │
│Flexible/│ │ System   │ │Evolution │
│Human Gate│ │          │ │          │
└─────────┘ └──────────┘ └──────────┘
     │             │           │
     └─────────────┼───────────┘
                   ▼
          ┌────────────────┐
          │ Three-Layer    │
          │ Controllability│
          │ Visible/       │
          │ Controllable/  │
          │ Reversible     │
          └────────────────┘

Quick Navigation

Concept	One-Sentence Explanation	When to Read
Naming Philosophy	The origin and deeper meaning of the DesireCore name	Want to understand the brand
Digital Companion	DesireCore agents are not tools, but "digital colleagues" you cultivate	Want to understand product positioning
Delegation Model	From "Q&A" to "I teach, you do"	Want to understand interaction patterns
AgentFS Filesystem	Each agent's "home" where all capabilities and memories exist as files	Want to understand data storage
Hardened/Flexible/Human Gate	Making agents as flexible as humans yet as controllable as software	Want to understand control mechanisms
Receipt System	Agents submit "work reports" after completing tasks	Want to understand audit trails
Self-Evolution	The secret to understanding you better over time	Want to understand agent growth
Three-Layer Controllability	Visible, Controllable, Reversible — you always hold the initiative	Want to understand safety guarantees
Compute Model	Bring your own keys, choose your own engines	Want to understand AI model configuration
Task Orchestration	Automatic task decomposition and best-agent matching — your "project manager"	Want to understand task distribution
Auto Dream	Lossless forgetting — preserving value through compression	Want to understand memory consolidation
Agent Permission Boundaries	Whoever acts is bound by their own ceiling; accountability for overreach lies with the executor	Want to understand permissions across collaborating agents
Enterprise Business Ontology	Connect business meaning and AI execution through objects, links, rules, actions, and permissions	Want to understand ontology, RAG, knowledge graphs, and FDE-style delivery

Reading Recommendations

If you're new to DesireCore, we recommend reading in this order:

1. Start with Digital Companion — understand "what makes it different"
2. Then read Delegation Model — understand "how to use it"
3. Next read Three-Layer Controllability — address concerns about "can I trust it"
4. Finally, explore other concepts based on your interests

If you have a technical background, you can jump directly to AgentFS Filesystem and Receipt System — these two concepts best demonstrate DesireCore's technical innovations.

If you lead enterprise AI or industry-solution delivery, continue with Enterprise Business Ontology to see how a real workflow becomes shared semantics, action boundaries, and acceptance evidence.