stack-guardian

mcp-name: io.github.LuminariSoftwares/stack-guardian

A health doctor for a home AI stack. It collects a snapshot of your nodes (Ollama endpoints, loaded models, NVIDIA GPUs, tailnet peers), runs small Python rules against it, remembers the last runs, and reports findings with a confidence grade: one sample is at most LIKELY, the same finding twice in a row is VERIFIED. A finding can carry a typed fix that you run on purpose, never automatically.

Status: 0.1.0, first release. Standard library only, Python 3.11+.

Install

pip install stack-guardian

This gives you three commands: stack-guardian (the CLI), stack-guardian-serve and stack-guardian-mcp.

Try it offline first: the example snapshot makes every shipped rule fire once.

curl -LO https://raw.githubusercontent.com/LuminariSoftwares/stack-guardian/main/examples/snapshot.json
curl -LO https://raw.githubusercontent.com/LuminariSoftwares/stack-guardian/main/examples/ctx.json
stack-guardian doctor --snapshot snapshot.json --ctx ctx.json

From a clone instead (for writing rules or running the tests):

git clone https://github.com/LuminariSoftwares/stack-guardian.git
cd stack-guardian
python -m venv .venv
.venv\Scripts\activate          # Windows;  macOS/Linux: source .venv/bin/activate
pip install -e .
stack-guardian doctor --snapshot examples/snapshot.json --ctx examples/ctx.json

For coding agents

• MCP server (any MCP client): stack-guardian-mcp speaks MCP over stdio with three read-only tools, stack_health, stack_snapshot and explain. In Claude Code:

  claude mcp add stack-guardian -e STACK_GUARDIAN_NODES=/path/to/nodes.json -- stack-guardian-mcp
  

  Other clients: command stack-guardian-mcp, args ["--nodes", "/path/to/nodes.json"]. stack_health grades against the saved run history without adding to it, and reuses one snapshot for 10 s (--ttl SECONDS).

• DSH plugin (npm install dsh-stack-guardian, source in dsh/, Node 20+): adds one line at the start of a DeepSeek Harness session when the doctor reports WARN or FAIL, and nothing otherwise. It runs stack-guardian doctor --json --quiet, so set STACK_GUARDIAN_NODES to your nodes file in the harness environment.

• Watching and scraping: stack-guardian doctor --watch 30 --json prints one JSON object per finding that changes state (new, resolved, severity change), so an agent can tail it; stack-guardian-serve --nodes FILE also answers GET /metrics in Prometheus text format.

What it does

1. doctor - run the checks

Describe your nodes in a JSON file (see examples/nodes.json) and check them live:

stack-guardian doctor --nodes examples/nodes.json --ctx examples/ctx.json

With neither --snapshot nor --nodes, doctor reads the nodes file named by $STACK_GUARDIAN_NODES.

Options: --checks-dir DIR (your own rules, default is the shipped checks.d), --ctx FILE (rule settings such as the model each node is expected to hold), --state FILE (default $STACK_GUARDIAN_STATE or ~/.stack-guardian/state.json), --json, --quiet (print nothing when all is OK).

Exit codes: 0 all OK/INFO, 1 a WARN, 2 a FAIL, 3 usage, 4 the doctor itself crashed.

Shipped rules: node.unreachable, ollama.unreachable, model.not_loaded, model.expiring, model.slow_ttft, vram.unattributed, gpu.unavailable, tailnet.unavailable, tailnet.peer_offline, tailnet.relayed. Each raises one finding per affected node. A rule that raises becomes a check.crashed WARN - a buggy rule never reports a broken stack.

LM Studio, vLLM, llama.cpp server. Give the node "kind": "openai" and list its base URLs under endpoints. It is read from GET /v1/models (and GET /v1/models/<id> when the server has it) into the same shape as an Ollama endpoint, so every rule above applies; a model a server lists as unloaded does not count as loaded.

{"gpu-box": {"kind": "openai", "endpoints": ["http://127.0.0.1:1234"]}}

model.expiring (WARN): a loaded Ollama model whose /api/ps expires_at is within 60 s of the snapshot time; INFO when /api/ps is unavailable. Change the window with "model_expiring_s": 120 in --ctx.

--watch N re-runs the doctor every N seconds and prints only the findings that changed state, each with a timestamp. Ctrl+C exits 0 with a one-line summary. With --json, each change is one JSON object on stdout.

stack-guardian doctor --nodes examples/nodes.json --watch 30

--ttft sends a 1-token generation to every loaded model on each Ollama endpoint and records ttft_ms on the model in the snapshot. It costs a generation, so it never runs unless you pass it, and it needs --nodes. The probe keeps each model's unload time as it was. model.slow_ttft (INFO) fires above 2000 ms; change it with "ttft_slow_ms": 1500 in --ctx.

stack-guardian doctor --nodes examples/nodes.json --ttft

2. doctor --fix ID - run a finding's typed fix

A rule may attach fix={"action": ..., "args": {...}} to a finding. There are exactly three actions and never a raw shell string:

action	what it does	needs
unload_model	POST keep_alive: 0 to an Ollama /api/generate	node, url, model
restart_lane	runs the argv list you declared for that lane	lane declared in --config
set_env	writes NAME=value to <state folder>/env and sets it for the process	name, value

stack-guardian doctor --checks-dir examples/checks.d --snapshot examples/snapshot.json --fix ollama.stuck --config examples/lanes.json

That is a dry run: it prints the plan and changes nothing. Add --apply to perform it. An applied fix first saves the snapshot under <state folder>/snapshots/, then runs, then appends one JSON line to <state folder>/fixes.jsonl (--audit FILE to move it). A set_env value is never written to the audit, only its length. ID is the finding code, or code@node when several nodes raise the same code. With --fix, the exit code is the fix's: 0 plan or success, 1 refused or failed, 3 usage.

3. Other commands

• stack-guardian snapshot --nodes FILE [--ttft] prints the raw snapshot the rules read.

• stack-guardian-serve --nodes FILE [--ctx FILE] [--port 8788] serves a fresh snapshot at GET /snapshot (read-only, loopback unless you pass --host H --allow-remote), so one machine can ask another for its health. no auth: bind to localhost or a tailnet IP only.

• The same server answers GET /metrics in Prometheus text format, running the shipped rules on a fresh snapshot: stack_guardian_finding{code,severity,node} (1 while raised, 0 once resolved), stack_guardian_worst_severity (0 OK, 1 INFO, 2 WARN, 3 FAIL) and stack_guardian_last_run_timestamp.

  curl http://127.0.0.1:8788/metrics
  

• stack-guardian-mcp --nodes FILE [--ctx FILE] [--state FILE] [--ttl SECONDS]: see For coding agents.

Writing a rule

from stack_guardian import finding as F

def ollama_up(snapshot, ctx):
    if not snapshot["nodes"]["gpu-box"].get("reachable"):
        return F.make_finding("ollama.unreachable", "missing", "FAIL", "gpu-box", "Ollama does not answer")
    return None

CHECKS = [("ollama.up", ollama_up)]

Drop the file in a folder and point --checks-dir at it. A full example with a fix is in examples/checks.d/20_ollama_fix.py. A rule may also return a list of findings, one per node.

Examples

file	what it is
examples/nodes.json	three nodes: a local one with GPUs, two remote ones over the tailnet
examples/ctx.json	rule settings: which model gpu-box-2 should hold
examples/snapshot.json	an offline snapshot on which every shipped rule fires once, for trying doctor and --fix
examples/lanes.json	the lanes restart_lane is allowed to run
examples/checks.d/20_ollama_fix.py	a custom rule whose finding carries a fix

Test

pip install pytest
python -m pytest -q

CI runs this on Ubuntu, Windows and macOS with Python 3.11, plus a privacy scan of every tracked file.

License

MIT