by zylos-ai
Give your AI a life — open-source infrastructure for persistent, self-maintaining AI companions. Powered by Claude Code.
# Add to your Claude Code skills
git clone https://github.com/zylos-ai/zylos-corePowered by Claude Code
</div>Claude Code is a genius — but it wakes up with amnesia every session. No memory of yesterday, no way to reach you, no ability to act on its own.
Zylos gives it a life. Memory that survives restarts. A scheduler that works while you sleep. Communication through Telegram, Lark, or a web console. Self-maintenance that keeps everything running. And because Claude Code can program, it can evolve — building new skills, integrating new services, growing alongside you.
Prerequisites: Git, Node.js >= 20 (via nvm recommended), a Linux server (or Mac), and a Claude subscription.
Why nvm? Installing Node.js via nvm avoids permission issues with
npm install -g. System-level Node.js (from apt/yum) requiressudofor global installs, which can cause problems.
# Install (--install-links required for GitHub install; will be published to npm soon)
npm install -g --install-links https://github.com/zylos-ai/zylos-core
# Initialize — sets up tmux, PM2, memory, scheduler, and more
zylos init
No comments yet. Be the first to share your thoughts!
zylos init is interactive and idempotent. It will:
~/zylos/ directory with memory, skills, and servicesTalk to your agent:
# Attach to the Claude session
tmux attach -t claude-main
# Or add a messaging channel
zylos add telegram
zylos add lark
Most agent frameworks isolate sessions per channel — your AI on Telegram doesn't know what you said on Slack. Zylos is agent-centric: your AI is one person across every channel. The C4 communication bridge routes all messages through a single gateway — one conversation, one memory, one personality. Every message persisted to SQLite and fully queryable.
Other frameworks lose your AI's memory during context compaction — silently, without warning. Zylos prevents this with a two-step safeguard: when context reaches 75%, the system automatically saves all memory before compaction runs. Five-layer Inside Out memory (identity → state → references → sessions → archive) ensures the AI always knows what to keep and what to com...