Agent Architecture

The Agent Team

Autonomous specialists with their own memory, tools, and personality — coordinated by the Orchestrator on your SovereignNode.

Fundamentals

What Is an AIMOS Agent?

An AIMOS agent is an autonomous domain specialist that combines four core components:

M

Memory

Dedicated SQLite database with semantic, episodic, and procedural long-term memory.

S

Skills (Tools)

Domain-specific tool collection: SQL queries, REST calls, file operations, domain-specific functions.

L

LLM (Language Model)

Local model via local LLM runtime. The agent builds the complete prompt from system prompt, memory context, and user query.

C

Connector

Communication channel to the user: Telegram, email, voice, or dashboard.

AGENT Autonomous Specialist Memory SQLite + Embeddings Skills SQL, REST, File, Domain LLM LLM Runtime (lokal) Connector Telegram, E-Mail, Voice Memory + Skills + LLM + Connector = Agent

How It Works

The Agent as a Digital Employee

An AIMOS agent does not work like a chatbot — it works like a case worker with its own desk, its own filing system, and its own daily routine.

Memory

Remembers facts, corrections, preferences — permanently. Semantic search finds memories even with different wording.

Notes & Filing

Writes summaries, research results, and conversation notes into its own workspace — like a case worker maintains their filing cabinet.

Calendar

Appointments, deadlines, follow-ups. The agent sees at every interaction its due and overdue appointments — and acts proactively.

Todo List

Open tasks, delegations, waiting lists. Automatically updated during the Dreaming cycle.

Daily Routine

Once daily, the agent independently checks calendar, emails, and open tasks — even without anyone addressing it.

Dreaming

During quiet phases, the agent processes its conversations: extracts facts, updates notes and todo lists, consolidates its memory.

Teamwork

Agents communicate with each other — the finance agent asks the logistics agent for inventory values, without burdening the user.

Escalation

For complex questions, the agent automatically escalates to a more powerful AI model — anonymized and audit-proof logged.

The result: An AIMOS agent has everything a case worker needs — memory, notes, calendar, todo list, colleagues, a daily routine, and the ability to get help when needed. The only difference: It works around the clock, never forgets anything, and is available in seconds.

SKILL_REGISTRY

18 Skills in the Toolbox

Each agent receives exactly the skills it needs — modularly assembled from the central registry. Custom skills can be developed and added at any time — for any industry, any ERP system, any workflow.

Engineering

structural

9 Tools

FEM calculation, profile optimization, DXF processing, code compliance checks, BOM export.

file_ops

7 Tools

Read, write, search, list files. Workspace management with public/private separation.

brave_search

1 Tool

Web research via Brave Search API. Current information without cloud dependency.

Communication

email

2 Tools

Send and receive emails via IMAP/SMTP. HTML and attachments.

mail_monitor

3 Tools

POP3 mailbox monitoring. Detects new emails and automatically triggers actions.

voice_io

Kontext

Whisper STT + Piper TTS. Speech recognition and synthesis in all languages, processed locally.

Storage

shared_storage

3 Tools

Inter-agent file exchange via public/ folder. Read, write, list.

remote_storage

4 Tools

SFTP access to remote machines via Tailscale VPN. Fetch and deposit files from workstations.

Planning

scheduler

2 Tools

Scheduled tasks: daily routine, recurring checks, reminders.

calendar

4 Tools

Create, query, modify, delete appointments. Proactive reminders for due dates.

contacts

3 Tools

Contact management: people, companies, phone numbers, email addresses, notes.

persistence

3 Tools

Permanently store notes and key-value pairs. Agent-owned knowledge base.

Intelligence

hybrid_reasoning

1 Tool

Escalation to a stronger model. Anonymized request to cloud LLM for complex analyses.

tr_calendar_awareness

3 Tools

Turkish holidays, Ramadan, Kandil nights. Cultural context awareness.

football_observer

2 Tools

Football results and schedules. Proactive notifications for important matches.

Accounting

eta_firebird

4 Tools

ETA V8 accounting via Firebird/InterBase. Account queries, open invoices, daily overview.

eta_mssql

4 Tools

ETA V8 accounting via Microsoft SQL Server. Same functions, different database backend.

web_automation

2 Tools

Browser automation for web portals without API. Fill forms, extract data.

Connectivity

Currently Available Connectors

The agent communicates via connectors — standardized interfaces to users, systems, and other agents. New connectors are continuously developed and can be added at any time for your specific IT landscape.

Telegram

Text, voice messages, documents. Proactive messages for reminders, alerts, and results. Shared Listener for all agents.

E-Mail

IMAP/SMTP for sending and receiving. POP3 monitoring for incoming mailboxes. HTML format and file attachments.

Voice

Whisper STT + Piper TTS — completely local. Speech recognition and synthesis in all languages, without cloud services.

SFTP

File access to workstations via Tailscale VPN. Shared folder for DXF, PDF, Excel — encrypted and without open ports.

SQL Databases

PostgreSQL, MSSQL, Firebird — exclusively SELECT queries. No write access to production data. Read-only by design.

REST / SOAP API

Universal API connectivity for ERP, CRM, inventory management. GET, POST, PUT with configurable authentication.

3-Tier Memory

Long-Term Memory

Three memory types, hybrid search, and a Dreaming cycle for consolidation.

Semantic Facts & Knowledge "Stahlpreis Q1: 850 EUR/t" "Uyumsoft API: /api/v2/stock" "Lieferant X: 14 Tage Vorlauf" Episodic Experiences & Conversations "2026-03-15: Bestandsabfrage" "2026-03-18: Preisvergleich" "2026-03-20: CAD-Analyse" Procedural Workflows & Patterns "Order: Check→Approve→Book" "BOM-Export: DWG→Parse→CSV" "Inventur: SQL→Diff→Report" Hybrid Search: FTS5 + Vector Embeddings + RRF Fusion Relevance ranking combines keyword and semantic matches

Dreaming — Memory Consolidation via LLM Call

During idle time, the agent analyzes its conversations with an LLM call, extracts facts, updates notes and todo lists, consolidates its memory, and creates weekly reports.

Like the human brain during sleep — the agent condenses experiences into knowledge, removes redundant entries, and strengthens important connections. The result: more precise answers with lower token consumption.

Dreaming Cycle (Consolidation)

Like the human brain during sleep, AIMOS consolidates memories during idle time:

Collect Episodes All Conversations Detect Patterns LLM Analysis Condense Extract Facts Store Semantically Long-term Memory

Token Optimization

Cognitive Balance

Dynamic balance between memory depth and response length — within the limited context window.

Memory Depth Response Length 1 2 3 4 5 System Prompt Memory Response Context Window (e.g. 32k Tokens) More memory = less room for response (and vice versa)
Level Memory Response
1 Minimal Very long
2 Reduced Long
3 Balanced Medium
4 Deep Short
5 Maximum Minimal

Coordination

Agents in a Team

Inter-agent messaging, shared files, and architecturally enforced data privacy.

Inter-Agent Communication

Engineering Agent CAD Analysis Bill of Materials Logistics Agent Stock Check ERP Access PostgreSQL Relay message_relay Tabelle "Need steel inventory" Forwarding Ping-Pong Limit: max 3 rounds

Connector Families

Agents of the same connector family share a communication channel. Messages to the family are automatically routed to the responsible agent.

Ping-Pong Protection

Maximum 3 back-and-forth rounds between two agents per request. Prevents endless loops and uncontrolled token consumption.

Workspace & Internal Data Privacy

Each agent has its own workspace — like a locked desk. Only deliberately shared files are visible to others.

Engineer Private (locked) notes/, calendar.json contacts.json, todo.txt steel_profiles.json public/ (shared) stueckliste.pdf report_projekt_X.dxf Finance Agent Private (locked) notes/, calendar.json market_prices.json contacts.json public/ (shared) kalkulation_projekt_X.pdf read_public blocked public/ — all agents can read privat — nur der eigene Agent File exchange via read_public Access denied

public/ — Bewusste Freigabe

Reports, exports, BOMs — everything other agents need. The agent decides what to share.

Privater Bereich — Unsichtbar

Notes, calendar, contacts, todo lists, profile databases. No other agent has access — architecturally enforced, not by policy.

Example: The engineering agent reads a DXF file from the engineer's workstation, creates a BOM, and places it in public/. The finance agent reads the BOM and calculates material costs — without access to the engineering notes.

Security

Execution Rings

Three trust levels determine which tools an agent may use. Like an operating system kernel.

Ring 2 — Full Access Ring 1 — Standard Ring 0 Read Only sql_query, rest_get memory_search, file_read file_write, sql_execute rest_post, email_send shell_exec memory_recall config_read
0

Ring 0 — Read Only

Lowest risk. The agent may only read: recall memory, view configuration. No access to external systems, no write access.

memory_recall config_read time_now
1

Ring 1 — Standard

Read access to external systems. SQL SELECT, REST GET, file read. No write access to production data. Standard ring for most agents.

sql_query rest_get file_read memory_search brave_search
2

Ring 2 — Full Access

Full access including write operations. Requires explicit authorization by the administrator. Human-in-the-loop for critical actions.

file_write sql_execute rest_post email_send shell_exec

Practical Examples

Example Agents

Three preconfigured agent types for typical industrial environments.

Engineering Agent

Ring 1 — Standard

Calculates structures with integrated FEM engine (PyNite), optimizes steel profiles by weight and cost, checks seismic codes (TBDY 2018, Eurocode). Creates BOMs as drafts — the engineer reviews and approves.

Skills
fem_calc profile_optimize seismic_check bom_generate
Connectors
PyNite FEM DXF TBDY 2018 Eurocode

Logistics Agent

Ring 1 — Standard

Connects Uyumsoft, SAP, Navision, and other ERP systems. Monitors inventory levels in real-time, reports critical shortfalls, and automates purchase requisitions via SQL and REST connectors.

Skills
sql_query rest_get stock_check alert_send
Connectors
Uyumsoft SAP RFC Navision REST

Finance Agent

Ring 1 — Standard (Schreiben: Ring 2)

Integrates ETA V8, DATEV, and other accounting systems. Analyzes cash flow, prepares bookings, and delivers up-to-date balances. Booking finalization only by authorized clerks.

Skills
sql_query cashflow_calc booking_prep datev_export
Connectors
ETA V8 DATEV Firebird MSSQL

These are examples. AIMOS agents are individually configured per company — each agent is tailored to the specific systems and requirements.