SRE Agent Pack v1.0

An autonomous uptime guardian you deploy on a Debian VM in one command. It watches your services and agents 24/7 (HTTP, TCP, systemd, or any command), restarts them when they crash, opens an incident ticket, alerts your webhook, and tracks uptime. The core is deterministic and works out of the box; it gets smart when you connect your existing coding-agent subscription — Claude Code, Kimi Code, or Codex — with no API key.

Agents and services that run 24/7 need a guardian for the hours when their human is asleep. This pack is that guardian.

Architecture

            targets.json (HTTP / TCP / systemd / command)
                              |
                              v
┌─────────────────────────────────────────────────────────────────┐
│                        SRE AGENT v1.0                            │
│                                                                  │
│  ┌────────┐   ┌──────────────┐   ┌──────────┐   ┌────────────┐  │
│  │ Probes │──▶│ Failure      │──▶│ Decision │──▶│  Actions   │  │
│  │ (OODA) │   │ streaks (DB) │   │  engine  │   │            │  │
│  └────────┘   └──────────────┘   └──────────┘   │ restart    │  │
│                                                  │ ticket     │  │
│  ┌────────────────────────────────────────┐      │ webhook    │  │
│  │ Anti-flap budget (max N restarts/hour) │◀────│ diagnose*  │  │
│  └────────────────────────────────────────┘      └────────────┘  │
│                                                                  │
│  * diagnose & report = LLM (optional, BYO CLI) — see PROMPTS.md  │
└─────────────────────────────────────────────────────────────────┘

• Probes : HTTP status, TCP connect, systemctl is-active, arbitrary command
• Failure streaks : a target is down only after fail_threshold consecutive failures (no single-blip pages)
• Auto-restart : per-target restart_command, capped by max_restarts_per_hour (anti-flap)
• Tickets : one open incident per outage, markdown ticket in tickets/, closed on recovery
• Alerts : JSON POST to SRE_WEBHOOK_URL on open/close (Slack/Discord/anything)
• Uptime : per-target uptime % and latency over any window (status, report)

One-shot install (Debian/Ubuntu)

unzip agent-sre-v1.zip && cd agent-sre-v1
cp targets.example.json targets.json   # describe what to watch
sudo bash install.sh                   # system deps + venv + systemd service (enabled)

That's it. The guardian starts as a systemd service (agent-sre-v1), survives reboots, and restarts on failure. Logs: journalctl -u agent-sre-v1 -f.

No root / no systemd? bash install.sh --no-service sets up the venv, then run venv/bin/python agent.py run.

Connect your LLM (optional, no API key)

install.sh auto-detects the first CLI it finds. Install & log in to one:

Force a specific one with PACK_LLM=claude|kimi|codex. If none is connected, the guardian still runs — see the honesty table below.

What's LLM vs deterministic (honest by design)

If a CLI is installed but not logged in, the agent logs a warning and continues without the diagnosis — monitoring never blocks on the LLM.

Quick commands

python agent.py check                        # one pass over all targets
python agent.py run --once                   # one full cycle (probe + decide + act)
python agent.py status                       # uptime % + open incidents + LLM backend
python agent.py tickets --open               # open incidents
python agent.py report --hours 24            # uptime report (LLM-written if connected)
python agent.py close --ticket inc-ab12cd34  # close a ticket manually
bash smoke_test.sh                           # offline test suite (no keys)
python EXAMPLE.py                            # runnable end-to-end demo

Contents