Skip to content

XYBEROS AI Platform

XYBEROS is a Python framework for building cognitive AI systems — agents that can perceive, reason, plan, act, reflect, and remember.

Quick Start

pip install xyberos

from xyberos import xyberos

ctx = xyberos.chat("Hello, world!")
print(ctx.thought.summary)

Why XYBEROS?

Concept XYBEROS gives you
Cognitive pipeline Perceive → Reason → Plan → Decide → Act → Reflect → Remember
Pluggable everything 12 entry-point groups, 54 auto-discovered plugins
Security Authentication, authorization, RBAC, Guardian decision engine, risk scoring, audit trail, capability management, policy engine, human-in-the-loop approval, resource governance
Multi-agent Built-in agent communication, shared memory, task delegation
Memory 6-tier memory with automatic fallback and promotion
Model-agnostic OpenAI, Anthropic, Ollama, or any OpenAI-compatible backend
REST API FastAPI server with OpenAPI docs
Zero config Sensible defaults — works out of the box

Architecture

XYBEROS Facade (xyberos singleton)
      │
      ▼
 Cognitive Brain — Perceive → Attend → Reason → Plan → Decide → Act → Reflect → Remember
      │
      ▼
 Pluggable Modules — Processors · Providers · Strategies · Tools · Agents · Skills · Knowledge
      │
      ▼
    Memory — Working → Episodic → Semantic → Procedural → Vector → Knowledge Graph
      │
      ▼
 Storage & Database — In-Memory ↔ Local Filesystem / SQLite
      │
      ▼
    Kernel — Services · Container · Lifecycle

Next Steps