Celistra Blog

Celistra Setup Guide: From Download to First Agent in 5 Minutes

Step-by-step. Download the daemon. Pair your first machine. Spawn Claude Code. Watch from your phone. Sandbox a permission. Five minutes, no SSH keys, free for 1 node.

Apr 19, 2026

Is ngrok Safe for Your Home Server? An Honest Risk Assessment

ngrok is convenient but routes your traffic through a third-party relay. Here's the actual threat model, what ngrok sees, and when self-hosted alternatives (Cloudflare Tunnel, bore, Celistra's tunnel) are worth the switch.

Mar 30, 2026

Run Claude Code on Every Machine You Own

A laptop, a GPU rig, a homelab box, an old Mac mini under the TV. Here's how to run Claude Code on all of them and supervise everything from one dashboard — or your phone.

Mar 26, 2026

Sandboxing Claude Code on macOS: Stop Yolo Mode Without Losing Power

--dangerously-skip-permissions is fine until it isn't. Here's how to wrap Claude Code in macOS Seatbelt with capability tokens — workspace-only writes, network on/off, screen recording per-grant.

Jan 17, 2026

Keep a Claude Code Session Alive After Closing the Terminal

Claude Code's Remote Control documentation says 'your terminal must remain open.' Here's how to make that not be true — using a daemon that owns the agent, not your shell.

Dec 11, 2025

Git Worktrees + Celistra: Parallel Claude Code Sessions With Full Supervision

Git worktrees solve 'agents fighting over node_modules.' Celistra solves 'where is each agent running.' Combine them and you have N independent CC sessions, all visible from one screen.

Nov 04, 2025

The Audit Log Every AI Agent Needs

If something weird happens, can you say what the agent did? A hash-chained, append-only audit log is the difference between investigation and guesswork.

Oct 16, 2025

Tailscale vs Cloudflare Tunnel vs Bore: What I Use For My Daemon's Tunnel

Best ngrok alternative that keeps data on your own hardware. Self hosted tunnel vs ngrok for home server remote access. Honest review of three reverse-tunneling stacks: when each is right.

Oct 06, 2025

Run 10 Claude Code Instances in Parallel — From Your Phone

Spawn 10 Claude Code agents on different machines, each with a different task, supervised, sandboxed. Approve permission requests with a haptic tap. The fleet is in your pocket.

Sep 22, 2025

Approve Every Agent Action From Your Phone (Haptic Approvals)

When an agent asks for permission, the phone buzzes. Long-press to approve, swipe to deny. The whole loop is sub-second. Here's why it matters and how it's built.

Sep 15, 2025

Watching Every Process on Every Box You Own (Demo Walkthrough)

Multi-machine dashboard for remote process control. Manage and monitor processes across all your machines from a single interface — no SSH per box. 5-minute walkthrough.

Aug 17, 2025

When Kubernetes Is Overkill: A Process Orchestrator for Homelab

Best process manager for homelab servers in 2026. Lightweight process orchestration for NAS, GPU rig, Raspberry Pi. K3s alternative for homelab enthusiasts who don't need pod scheduling.

Aug 04, 2025

What Is Zero-Trust Process Orchestration?

A short, opinionated definition. Zero-trust process orchestration is a control plane for spawning, supervising, and killing processes across machines you own — where every action is authenticated, every grant is explicit, and every decision is in an audit log.

Jul 26, 2025

Best Process Manager for Homelab in 2026: PM2, Supervisor, systemd, Celistra Compared

Six process managers ranked by what they're actually good at: systemd, Supervisor, PM2, Docker Compose, Portainer, Celistra. With the decision matrix that says which one for your homelab.

Jul 08, 2025

LAN-Direct Routing: Sub-Millisecond Latency for Local Dashboards

When you're on the same Wi-Fi as your daemon, the dashboard talks to 127.0.0.1 directly. Round-trip is ~0.3ms — better than any cloud relay. Here's how the probe works and why it matters.

Jun 26, 2025

Restart-on-Crash for Long-Running AI Agents

AI agents crash. Models 500. Network blips. Worth keeping the lights on. Here's a small ceiling-and-backoff design that stops infinite respawns without giving up on transient errors.

Apr 18, 2025

Pair a Machine in 30 Seconds Without SSH Keys (Capability Tokens)

SSH key pairing is two-factor: 'something I have' (the key) plus 'something I authorized' (manual ssh-copy-id). Capability tokens collapse the second step into a one-time token issued by the tray.

Apr 16, 2025