Files
home/specs/architecture.md
2025-09-29 09:38:03 +08:00

47 lines
1.3 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Mycelium Agents Architecture Overview
## Personal Agents
- Every individual has a **Personal Agent (PA)**.
- The PA manages tasks, workflows, and digital life.
- It acts as the secure, sovereign interface to data and AI services.
## Worker Agents
- Specialized agents that execute tasks such as research, coding, analytics, or operations.
- Activated and coordinated by Personal Agents.
## LLMs (Brains)
- Large Language Models provide reasoning, language understanding, and advanced knowledge.
- Accessed by Personal Agents and Worker Agents when higher cognitive capacity is needed.
## Network of Intelligence
- Agents communicate securely with each other.
- Private, encrypted peer-to-peer connections.
- Enables collaboration within and across organizations.
## Data Control
- All data stays under user or organization control.
- Agents use sovereign storage and secure communication.
## Architecture Diagram
```mermaid
%%{init: {'theme':'dark'}}%%
graph TD
H[Human User] --> PA[Personal Agent]
PA --> LLM[(LLM / Brain)]
PA --> WA1[Worker Agent: Research]
PA --> WA2[Worker Agent: Coding]
PA --> WA3[Worker Agent: Analytics]
%% Agents can collaborate
WA1 --- WA2
WA2 --- WA3
PA --- PAX[Other Personal Agent]
```