Self-hosted backup agent with restore checks

An autonomous backup agent you deploy on a Debian VM in one command. It runs a reliable deterministic core out of the box, and gets smart when you connect your existing coding-agent subscription — with no API key.

Architecture

+------------------+     +------------------+     +------------------+
|   Producer       | --> |   SQLite Queue   | --> |   OODA Loop      |
| (cron / CLI)     |     | (tasks + deps)   |     | (Executor)       |
+------------------+     +------------------+     +--------+---------+
                                                           |
                              +----------------------------+
                              |
                    +---------v----------+      +----------v---------+
                    |  Deterministic     |      |  LLM reasoning     |
                    |  backup handlers   |      |  (optional CLI)    |
                    +---------+----------+      +----------+---------+
                              |                            |
                    +---------v----------+      +----------v---------+
                    |  Dead-letter +     |      |  Retry / replay    |
                    |  prune / verify    |      |  idempotency       |
                    +--------------------+      +--------------------+

• Producer : cron, CLI (agent.py enqueue), or external API
• Queue : local SQLite, zero-config, zero-deps
• OODA Loop : observe, orient, decide, act
• Executor : deterministic handlers by default, LLM reasoning when a CLI is connected
• Retry : exponential backoff 10s -> 60s -> 600s
• Dead Letter : failed tasks kept, replayable

One-shot install (Debian/Ubuntu)

unzip agent-backup-v1.zip && cd agent-backup-v1
sudo bash install.sh          # system deps + venv + systemd service (enabled)

The agent starts as a systemd service (agent-backup-v1), survives reboots, and restarts on failure. Logs: journalctl -u agent-backup-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 agent still runs.

LLM vs deterministic (honest by design)

If a CLI is installed but not logged in, the agent logs a warning and falls back to the deterministic handler for that task.

Quick commands

python agent.py status
python agent.py enqueue --type backup_file --payload '{"source":"/etc/hosts","dest_dir":"/backups"}'
python agent.py enqueue --type prune_backups --payload '{"directory":"/backups","retention_days":30}'
python agent.py run --once
python agent.py run --deterministic
python agent.py replay --task t-ab12cd34
bash smoke_test.sh

Contents

Use a local model (Ollama)

The optional LLM step can also run on your own machine through Ollama, so no text leaves your server. No account and no API key.

ollama pull <model>               # any chat model you like
export PACK_LLM=ollama            # prefer Ollama even if a coding-agent CLI is installed
export PACK_OLLAMA_MODEL=<model>  # optional: default is the first chat model the server lists
python3 -c "import llm_adapter; print(llm_adapter.detect())"   # prints: ollama

• PACK_OLLAMA_HOST points to another server (default http://127.0.0.1:11434); OLLAMA_HOST is also read when PACK_LLM=ollama.
• PACK_OLLAMA_NUM_CTX sets the context size if your reports or prompts are long.
• Without PACK_LLM, a local Ollama server is used only when no Claude Code, Kimi Code or Codex CLI is found.
• If the server is down or the model is missing, the pack keeps working in its deterministic mode.

Learning memory (local and private)

Every LLM call this pack makes is journaled in ./.pack_memory/ next to the code, so the pack can improve for you. Nothing is ever sent anywhere.

• What is kept: the task name, the masked input, the masked answer, status and latency. Keys, tokens, e-mails, phone numbers, IP addresses, card and IBAN numbers and personal paths are masked before writing; the system prompt is never stored.
• Teach it: python3 pack_memory.py feedback last ok confirms a result, python3 pack_memory.py feedback last bad --fix "the right answer" corrects it. Confirmed and corrected runs are reused as validated examples when a similar input comes in. Unrated runs are never injected into a prompt.
• Find similar cases: python3 pack_memory.py similar "some text" and python3 pack_memory.py clusters (groups of near-identical failures) work in plain Python, no model needed. Optional meaning-based matching uses an embedding model you already run locally: python3 pack_memory.py enable-semantic (Ollama on this machine only).
• Share, only if you want: python3 pack_memory.py export writes an anonymised summary (counts, statuses, size buckets, no text) for you to review.
• Control: PACK_MEMORY=0 turns it off, PACK_MEMORY_STORE_TEXT=0 keeps fingerprints only, python3 pack_memory.py purge --yes wipes it.