...
This commit is contained in:
1
.gitignore
vendored
Normal file
1
.gitignore
vendored
Normal file
@@ -0,0 +1 @@
|
||||
target/
|
661
examples/Cargo.lock
generated
661
examples/Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
48
specs/agent_proxy_secure1.md
Normal file
48
specs/agent_proxy_secure1.md
Normal file
@@ -0,0 +1,48 @@
|
||||
# Agent Proxy Ultra Secure Level 1
|
||||
|
||||
- **Personal Agents (PA):** Linked to each human, manage tasks and access to data.
|
||||
- **Worker Agents:** Specialized executors triggered by Personal Agents.
|
||||
- **LLMs (Brains):** Provide reasoning and advanced language/knowledge.
|
||||
- **Proxy Agents:** Act as intermediaries between Personal Agents.
|
||||
- Changeable identity
|
||||
- Preserve privacy & sovereignty
|
||||
- Prevent direct PA-to-PA exposure
|
||||
|
||||
|
||||
### 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]
|
||||
|
||||
%% Proxy Layer
|
||||
PA --> Proxy[Proxy Agent]
|
||||
Proxy --> PAX[Other Personal Agent]
|
||||
|
||||
%% Worker examples for other PA
|
||||
PAX --> WA3[Worker Agent: Analytics]
|
||||
|
||||
```
|
||||
|
||||
## Proxy Agent
|
||||
|
||||
- **Function:** Acts as a go-between for Personal Agents, ensuring no direct connection.
|
||||
- **Identity:** Can change or mask identity to enhance privacy.
|
||||
- **Security:** Prevents direct exposure of Personal Agents to each other.
|
||||
- **Use Cases:** Ideal for sensitive communications, cross-organization tasks, or when anonymity is needed.
|
||||
|
||||
Difference with other implementations
|
||||
|
||||
- works for all hero functionality, not just chat
|
||||
- can be implemented multi level (proxy of proxy)
|
||||
|
||||
## Flow Example
|
||||
|
||||
- Proxy Agent changes public key (max 1x per week)
|
||||
- User can chose if personal secure friends (a white list) receive the updated public key automatically
|
42
specs/agent_proxy_secure2.md
Normal file
42
specs/agent_proxy_secure2.md
Normal file
@@ -0,0 +1,42 @@
|
||||
# Agent Proxy Ultra Secure Level 2
|
||||
|
||||
- **Personal Agents (PA):** Linked to each human, manage tasks and access to data.
|
||||
- **Worker Agents:** Specialized executors triggered by Personal Agents.
|
||||
- **LLMs (Brains):** Provide reasoning and advanced language/knowledge.
|
||||
- **Proxy Agents:** Multi-level intermediaries between Personal Agents.
|
||||
- Changeable identity
|
||||
- Stateless, can move across nodes daily
|
||||
- Preserve privacy & sovereignty
|
||||
- Prevent direct PA-to-PA exposure
|
||||
|
||||
|
||||
### 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]
|
||||
|
||||
%% First proxy
|
||||
PA --> Proxy1[Proxy Agent Level 1]
|
||||
|
||||
%% Second proxy
|
||||
Proxy1 --> Proxy2[Proxy Agent Level 2]
|
||||
|
||||
%% Connection to other PA through Proxy chain
|
||||
Proxy2 --> PAX[Other Personal Agent]
|
||||
|
||||
%% Worker for the other PA
|
||||
PAX --> WA3[Worker Agent: Analytics]
|
||||
```
|
||||
|
||||
### Ultra Ultra Secure
|
||||
|
||||
- stateless design, can move across nodes daily
|
||||
- leave no trace when moved
|
||||
|
46
specs/architecture.md
Normal file
46
specs/architecture.md
Normal file
@@ -0,0 +1,46 @@
|
||||
|
||||
# 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]
|
||||
|
||||
```
|
Reference in New Issue
Block a user