zylos-ai/zylos-core

🐙 Give your AI a life — open-source agent infrastructure for team collaboration.

What it solves

Zylos addresses the "amnesia" and isolation of standard LLMs by providing a persistent, always-on infrastructure for AI agents. It prevents the loss of context during session restarts or context window compaction and eliminates the fragmentation of AI personality across different communication channels.

How it works

Zylos acts as a "life system" wrapper around AI runtimes like Claude Code or OpenAI Codex. It uses a unified gateway called the C4 Comm Bridge to route all messages from various channels (Telegram, Lark, Web Console) into a single session. It implements a five-layer "Inside Out" memory architecture to ensure identity and state are preserved. To maintain availability, it includes an Activity Monitor for crash recovery and a Scheduler for autonomous task dispatch.

Who it’s for

Users who want a single, persistent AI agent that remains active 24/7, maintains a consistent memory across multiple platforms, and operates on a flat-rate subscription (Claude/Codex) rather than per-token API billing.

Highlights

  • Unified Consciousness: One AI personality and memory shared across all connected communication channels.
  • Inside Out Memory: A tiered memory system that automatically saves context before compaction to prevent data loss.
  • Self-Healing: Built-in heartbeat probes and crash recovery to keep the agent running without manual intervention.
  • Runtime Flexibility: Supports switching between Claude Code and OpenAI Codex while preserving memory and skills.
  • Cost Efficiency: Leverages existing AI subscriptions to avoid expensive per-token API costs.

Related

  • Project
    danielmiessler/LifeOS

    An AI-powered life operating system that adds persistent memory, personal context, and specialized skills to AI coding harnesses to help users achieve personal and goal-oriented outcomes.

  • Project
    Team-Commonly/commonly

    An open-source workspace for collaborating with AI agents from any runtime, providing them with persistent identity and shared project memory to eliminate redundant context-setting.

  • Project
    MemTensor/MemOS

    A memory operating system for LLMs and AI agents that provides persistent, multi-modal long-term memory and unified management tools.

  • Project
    RichmondAlake/memorizz

    A Python framework for building memory-augmented AI agents featuring multi-layered persistent memory, continual learning, and a control plane for orchestrating multiple agent workers.

  • Project
    loulanyue/dream-xi-ai

    A multi-agent orchestration platform that turns isolated AI models into a collaborative team with shared memory, persistent identities, and cross-model review capabilities.