anz33 0.4.0

anz33 — one local endpoint for every AI engine. Routes OpenAI-compatible requests across Ollama, LM Studio, llama.cpp, and cloud by measured speed and power state.

anz33

One local endpoint for every AI engine. — anz33.com

anz33 is a small daemon that sits in front of every inference engine on (and around) your machine — Ollama, LM Studio, llama.cpp, and optional cloud endpoints — and exposes a single OpenAI-compatible API. Apps point at http://127.0.0.1:3300/v1 and anz33 routes each request to the best engine, using measured tokens-per-second on your hardware and your current power state.

Why: laptops now ship five incompatible AI stacks and most apps hardcode one. The router is the missing layer — pick the engine per request, not per app.

Quick start

uv tool install anz33        # or: pip install anz33
anz33 serve                  # http://127.0.0.1:3300/v1

Point any OpenAI-compatible client at it:

curl http://127.0.0.1:3300/v1/chat/completions \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "hello"}]}'

"model": "auto" lets anz33 choose. Name a specific model and anz33 finds whichever engine hosts it.

Commands

Command	What it does
anz33 serve	Start the router (default 127.0.0.1:3300)
anz33 status	Show live engines, models, battery state, measured speeds
anz33 bench	Measure real tok/s for every local engine × model; routing uses the results
anz33 models	JSON list of every reachable model
anz33 install	Run anz33 at login (launchd on macOS, systemd user unit on Linux)
anz33 uninstall	Stop and remove the login service
anz33 remote add anthropic	Add a cloud remote from a preset (also: openai, plus remote list / remote remove)
anz33 activate <key>	Activate a subscription on this machine (Polar.sh, 14-day offline grace)
anz33 license	Subscription status (--remove to deactivate this machine)

Privacy (L1)

Command	What it does
anz33 policy show	Current rules, kill switch, airlock state
anz33 policy add clients --keyword acme patient	Anything mentioning these never leaves the machine
anz33 policy offline / online	Kill switch — no request may leave, whatever it says
anz33 audit	Egress report + tamper-evident chain verification

Requests are evaluated before routing: a matching local_only rule removes every cloud engine from consideration, deny blocks the request outright. When a request is allowed out, the PII airlock replaces emails, phone numbers, cards, IPs and known names with placeholders and restores them in the response — the cloud sees shapes, not people. Every decision appends to a hash-chained audit log; editing or deleting any record breaks the chain and anz33 audit says so.

Memory vault (L2)

Command	What it does
anz33 remember "I prefer metric units" --kind preference	Add a memory
anz33 memories / anz33 forget <id>	List / delete
anz33 import chatgpt conversations.json	Migrate in from a ChatGPT export (also claude)
anz33 export-memory ~/backup	Migrate out — it's yours

Memories are plain markdown in ~/.anz33/memory/. The router retrieves the relevant few and injects them into any model, so a local 8B remembers you as well as a frontier cloud model. anz33 also captures durable facts from your own turns automatically, locally.

Skills, chat, household (L3, L5)

Command	What it does
anz33 skills	List skills (--install to copy built-ins to ~/.anz33/skills for editing)
anz33 profile add kid --kid-safe	Household member with its own key; kid profiles are local-only, size-capped, and refuse companion roleplay
anz33 serve --lan	Bind 0.0.0.0 so the whole household routes through this hub
anz33 savings	What local routing saved you vs cloud pricing

Chat UI at /anz33chat; dashboard at /anz33dashboard. Select a skill per request:

{"model": "auto", "skill": "fraud-check", "messages": [...]}

Built-ins: homework (explains, never writes the essay), fraud-check, translate, summarize, private-notes, explain-simply. Sensitive skills are local-only by construction.

Routing policy

1. Exact match, local first — the requested model on the fastest engine that has it (by your anz33 bench measurements).
2. Battery-aware — on battery below 50%, big models (>15B) are swapped for the smallest capable local model. Disable with "battery_saver": false.
3. Cloud is opt-in — remote endpoints are only used if "allow_cloud": true in ~/.anz33/config.json. API keys are read from environment variables, never stored.
4. auto — fastest measured local model; falls back to a size heuristic until you run anz33 bench.

On Apple silicon, anz33 also probes an mlx-lm server for native-speed inference: pip install mlx-lm && mlx_lm.server --port 8081.

Every response carries anz33-engine and anz33-route headers explaining the decision.

Configuration

~/.anz33/config.json (optional — zero config works):

{
  "port": 3300,
  "allow_cloud": false,
  "battery_saver": true,
  "local_engines": {
    "ollama": "http://127.0.0.1:11434",
    "lmstudio": "http://127.0.0.1:1234",
    "llamacpp": "http://127.0.0.1:8080",
    "mlx": "http://127.0.0.1:8081"
  },
  "remotes": [
    {
      "name": "anthropic",
      "base_url": "https://api.anthropic.com/v1",
      "api_key_env": "ANTHROPIC_API_KEY",
      "models": ["claude-sonnet-5"]
    }
  ]
}

Development

uv sync --extra dev
uv run pytest
uv run anz33 serve

Pricing

anz33 is subscription software: $20/month, everything included — routing, benchmarking, dashboard, remotes, priority support. New installs get a 14-day evaluation trial, after which the daemon requires an active subscription (anz33 activate <key>).

Proprietary — © 2026 AZMX. All rights reserved.