My AI
Operating System
A personal framework that turns knowledge into autonomous action —
built on Claude Code + Gemini CLI, living inside a Git-versioned vault.
↓ scroll to explore
Architecture
4-Layer Stack
Each layer has a single responsibility. Information lives in exactly one place — if another layer needs it, it references it, never duplicates it.
~/.configfiles/aifiser/
Reproducibility. Bootstrap the entire system from zero on a new machine. Dotfiles, MCP server configurations, Claude Code settings and environment setup managed as versioned code.
~/.claude/ + ~/.mcp.json
Execution state. What the agent needs right now — 11 live MCP connections, permission matrix, slash commands and event hooks. Ephmeral but reproducible from Layer 1.
Nexus/ (PARA + 900-SYSTEM/)
Persistent knowledge base. Projects, areas, resources, 34 executable skills, session state and autonomous loop governance. Git-versioned with GitHub as the Single Source of Truth. Each active project has a dedicated NotebookLM notebook as its RAG layer — the agent queries it to retrieve context from specs, emails and decisions without loading everything into the prompt.
Nexus/003 - Resources/ (Systems/ + Connectivity/)
Technical graph of all production systems and their interfaces. Lazy-loaded — only read when diagnosing incidents or mapping impact. Enables bidirectional navigation between projects and the systems they touch.
Execution Model
Bicefalia
Two AI agents with complementary roles operating over the same vault. Neither is a generalist — each owns its domain.
Skills · 34 active
Executable Runbooks
A skill is a numbered, self-contained procedure that any agent can execute correctly without prior context. Each declares its inputs, outputs, MCP dependencies and failure mode.
Integrations
MCP Ecosystem
11 Model Context Protocol servers give the agent structured, typed access to external systems — far beyond what shell commands alone can provide.
Every session
Session Lifecycle
No context is assumed, none is lost. Every session follows a deterministic boot and close protocol — so the agent is always oriented, and handover between sessions is lossless.
git log --oneline
HANDOVER.md
MEMORY.md
#sev/critical scan
Pushover if breach
WORKSPACE staging
confirmation gate
HANDOVER.md ← state
git commit + push
System in Action
A real session, step by step
An AI agent session using Capa 4 topology, RAG knowledge retrieval, and multi-MCP orchestration — all names sanitised.
COLD START
Agent boots, reads HANDOVER.md and STATE.md to reconstruct prior session context. Runs git pull --rebase to sync vault.
CONTEXT LOAD — RAG
Queries the per-project NotebookLM notebook for domain context. Capa 3 KNOWLEDGE layer injects relevant architecture decisions without loading the full vault into the prompt.
INCIDENT DETECTED
Monitoring surfaces a #sev/high alert. Agent notifies via Pushover MCP and opens a ManageEngine ticket automatically — zero human touch.
LAYER 4 TOPOLOGY
Reads the Technical Map in Capa 4 TOPOGRAPHY. Graph nodes and connectivity edges pinpoint affected systems and downstream dependencies in seconds.
MULTI-MCP TRACE
Agent calls trace_data_flow skill, fanning out across three MCP servers in parallel: SAP backend, Analytics DB, and BI Workspace — assembling a unified trace timeline.
ROOT CAUSE
Cross-referencing trace data with RAG-retrieved past incidents, the agent identifies a schema drift introduced in the last deployment. Evidence packaged as structured output.
WORKSPACE STAGING
Proposed fix drafted in 900-SYSTEM/WORKSPACE/ sandbox. SharePoint MCP uploads runbook draft for review. ManageEngine ticket updated with resolution notes.
SESSION CLOSE
Agent writes HANDOVER.md, appends a row to STATE.md session log, commits vault snapshot, and pushes to GitHub — full audit trail preserved.
Want to know more?
See the system in action
Browse my portfolio for projects built on top of this framework, or reach out directly.