System Architecture
Claude Code + MCP Servers + Sub-Agents + Memory + Skills
Full System View
flowchart TB
subgraph Operator["Operator Layer"]
User["Colin / Human Operator"]
Voice["Voice Announcements<br/>Elisabeth · Finn"]
end
subgraph Orchestration["Orchestration Layer"]
CC["Claude Code CLI"]
Skills["Skills Engine<br/>12-Phase Coding · TDD · PDF Creator"]
Memory["Persistent Memory<br/>MEMORY.md + file-based"]
Tasks["Task Tracking<br/>Progressive completion"]
end
subgraph MCP["MCP Server Layer"]
Chrome["Chrome Browser<br/>Scraping + Testing"]
Linear["Linear<br/>Project Management"]
GitHub["GitHub<br/>Version Control"]
TTS["Edge-TTS<br/>Voice Synthesis"]
Sheets["Google Sheets"]
Gemini["Gemini Chat<br/>Cross-validation"]
OpenAI["OpenAI Chat<br/>Peer review"]
end
subgraph Agents["Agent Layer"]
Sub1["Research Agents ×6"]
Sub2["Scraper Agents ×10"]
Sub3["Analysis Agents ×4"]
Sub4["Dev Agents ×2"]
end
subgraph Output["Output Layer"]
Site["Astro Website<br/>23 pages"]
Report["Analysis Report<br/>96KB · 16 diagrams"]
Docs["Handover Docs<br/>CLAUDE.md · DEPLOY.md"]
end
User <--> CC
CC --> Skills
CC --> Memory
CC --> Tasks
CC <--> MCP
CC --> Agents
Voice --> User
Agents --> Output
MCP --> Agents
Layer by Layer
The orchestrator runtime. Manages context windows, spawns sub-agents, enforces governance rules, and coordinates the entire pipeline from a single terminal session.
Standardised tool interface. Each MCP server exposes capabilities — browser, project management, voice, spreadsheets — that agents can call via a uniform JSON-RPC protocol.
Reusable skill definitions (markdown files) encoding domain knowledge. Examples: bacon-evolutionary-coding (12-phase methodology), pdf-creator, test-guard.
File-based memory system surviving across sessions. Four types: user preferences, feedback loops, project state, and reference knowledge. Context never gets lost between agent lifetimes.
Parallel working directories sharing one repository. Multiple agents can work on different aspects simultaneously without merge conflicts or blocking each other.
22 specialised sub-agents — scrapers, researchers, analysts, developers — each spawned with full context inheritance. They run in parallel, report back, and are governed by the same SA rules.
Protocol Design
Each MCP server is a standardised JSON-RPC interface. Chrome browsers, Linear project management, Edge-TTS voice, Google Sheets — all accessed through the same protocol.
Adding new capabilities means adding a new MCP server — not modifying the framework. Need Slack integration? Deploy a Slack MCP server. The orchestrator discovers it automatically.
The Chrome browser MCP server lets agents literally browse the web — click buttons, fill forms, take screenshots, scrape content. Not simulated. Real browser automation.
Algorithmix used 7 MCP servers simultaneously: Chrome (scraping), Linear (tracking), GitHub (version control), Edge-TTS (voice), Google Sheets (data), Gemini and OpenAI (peer review).
Cross-Validation
BACON-AI does not just use Claude — it cross-validates with Gemini and GPT to catch model-specific blind spots.
Primary orchestrator
Runs the pipeline, generates content, spawns agents, writes code
Peer reviewer
Challenges assumptions, reviews analysis quality, provides alternative angles
Cross-validator
Root-cause analysis, debugging triage, validates solutions from a different perspective
After 3 failed fix attempts, mandatory triage is triggered
Claude shares the complete error context with both GPT and Gemini
All three models provide independent root-cause analyses
Solutions are synthesised, tested, and cross-validated before applying
“Three AIs disagreeing is more valuable than one AI agreeing with itself.”