The Individual Agent
Autonomous specialists with their own memory, their own tools, and personality — each agent is a specialized digital assistant.
Five Building Blocks
An AIMOS assistant is an autonomous specialist that combines five core components:
Controls the thinking process in phases: Observe, Orient, Act — following the OODA principle.
Dedicated SQLite database with semantic, episodic, and procedural long-term memory.
Domain-specific tool collection: SQL queries, REST calls, file operations, domain-specific functions.
Communication channel to the user: Telegram, email, voice, or dashboard.
Local model via LLM runtime. The assistant builds the complete prompt from system prompt, memory context, and user query.
The key point: The assistant prepares — you decide. Your expertise, your experience, and your judgment remain indispensable. The assistant takes routine work off your plate: gathering data, monitoring deadlines, preparing drafts. The expert work stays with you.
OODA Cycle
A chatbot reacts to each message individually. An AIMOS assistant opens its inbox, surveys everything, recognizes connections — and then acts in a coordinated way. The principle behind it: the OODA cycle from decision theory.
Reactive mode
OODA mode
Thread tg:smith
Developer Smith
"Unit tests for SG-03 are complete."
Thread email:req-manager
Requirements Manager
"TSR-17 has been upgraded to ASIL D."
Thread int:testmgr
Test Manager
"Integration test for SG-03 is failing."
SITUATION REPORT (cross-thread)
"All three messages concern Safety Goal SG-03. The ASIL D upgrade of TSR-17 changes the verification requirements: Smith's unit tests are no longer sufficient (MC/DC coverage required). The failing integration test is a separate timing issue."
→ To Smith
"Tests completed, but due to ASIL D upgrade, statement coverage is no longer sufficient. MC/DC required."
→ To Requirements Manager
"Upgrade registered. 3 SW requirements affected, unit tests need to be extended. Impact analysis attached."
→ To Test Manager
"Timing issue, not caused by ASIL upgrade. Please send logfile. Integration test must be repeated after unit test extension."
Each stakeholder receives only what is relevant to them — but every response is informed by the big picture.
The orchestrator is not an AI model, but deterministic code. It controls the OODA cycle by calling the LLM multiple times with different tasks:
The situation report lives only during a batch run. It is not stored — next run, new report. Long-term insights migrate to memory.
The assistant knows the big picture, but stakeholder A learns nothing about the conversation with stakeholder B — only about impacts relevant to them.
The phase sequence is deterministic. The LLM cannot skip or mix phases — it receives a clear task for each phase.
Three Modes
AIMOS supports three agent types — from quick voice responses to structured case workers. All three can act proactively (cronjobs, reminders, follow-ups).
<500ms latency
Immediate reaction to voice input. Whisper transcription parallel to LLM warmup. Short, precise responses.
Reception, voice control, quick queries
<5s latency
Quick conversation via Telegram, email, or dashboard. Memory, customer records, delegation to colleagues. Cronjobs for proactive reminders.
Customer support, helpdesk, order intake
Batch — OODA cycle
Checks its inbox, surveys all processes, recognizes cross-thread connections, builds a situation report — and then acts in a coordinated way.
Process management, compliance, project assistance
All three types have memory, skills, connectors, and can act proactively. The difference is in the thinking approach: one thread vs. the big picture.
3-Tier Memory
Three memory types, hybrid search, and a Dreaming cycle for consolidation.
In idle state, the agent analyses 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.
Like the human brain during sleep, AIMOS consolidates memories during idle time:
Language Model
The Large Language Model (LLM) is the thinking engine behind every agent. It understands language, makes decisions, and controls tools — and runs entirely on your own hardware.
Your queries never leave the network. No cloud provider sees your data.
No per-query Token price. The model runs unlimited on your GPU.
No API limit, no rate limiting, no dependency on external services.
For complex tasks: automatic, anonymized escalation to a cloud LLM. → Details
Integration
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.
Text, voice messages, documents. Proactive messages for reminders, alerts, and results. Shared listener for all agents.
IMAP/SMTP for sending and receiving. POP3 monitoring for incoming mailboxes. HTML format and file attachments.
Whisper STT + Piper TTS — fully local. Speech recognition and synthesis in all languages, without cloud services.
File access to workstations via Tailscale VPN. Shared folders for DXF, PDF, Excel — encrypted and without open ports.
PostgreSQL, MSSQL, Firebird — SELECT queries only. No write access to production data. Read-only by design.
Universal API integration for ERP, CRM, inventory management. GET, POST, PUT with configurable authentication.
Thread Architecture
Every conversation gets its own thread ID. The assistant only ever sees the current customer — no matter how many run in parallel.
Every customer automatically gets their own thread. Telegram user A never sees the conversation of email customer B.
A customer writes via Telegram: “I sent you an email.” The assistant finds the email thread and instantly has the context.
When an assistant delegates a task to a colleague, the thread ID travels along. The recipient works in the same customer context.
Automatic Assignment — every channel generates the correct thread ID on arrival
Email Threading — In-Reply-To and References headers for correct matching
Files per Thread — attachments are assigned to the process, cross-channel
Code-Level Isolation — enforced at the database level, not dependent on the AI model
Toolbox
Each AI assistant receives exactly the skills it needs. Custom skills can be added at any time — for any industry, any system, any workflow.
IMAP/SMTP, POP3 monitoring. Send, receive, attachments, automatic mailbox monitoring.
Text, voice messages, documents. Proactive notifications for alerts and results.
Whisper STT + Piper TTS — fully local. Speech recognition and synthesis in all languages.
Read and send channel messages, create online meetings. Microsoft Graph API.
Search, create, update issues and change status. JQL queries, sprint overview.
Work items, pipelines, boards. Create tasks, track status, monitor CI/CD.
Read projects and tasks, track milestones, update deadlines.
Requirements, test cases, traceability links, baseline comparison. For automotive development.
Wiki pages and documents — read, create, update. DMS integration.
Create Office documents: reports as Word, data as Excel, presentations as PowerPoint.
Scan invoices, delivery notes, contracts. Auto-detect fields. Processed locally.
Daily and weekly summaries, CSV export, automatic overviews.
Query articles, customers, orders, inventory levels. Multi-backend: SAP, DATEV, custom.
PostgreSQL, MSSQL, Firebird — read-only by design. No write access to production data.
Repositories, merge requests, CI/CD pipelines. Read commits, create issues, comment.
File access to workstations via VPN. Encrypted and without open ports.
Certifications, maintenance intervals, contract terms. Proactive reminders before expiry.
Monitor stock levels, reorder suggestions, minimum quantity alerts.
Appointments, deadlines, follow-ups. Send Outlook invitations. Public holidays automatically considered.
People, companies, phone numbers, email addresses. Automatic updates.
Modular Toolbox: Each AI assistant receives only the skills it needs. Custom integrations (specialized ERP systems, industry-specific tools, internal databases) can be developed and added as new skills at any time — without changing the core.