neuralosd — deterministic-first agentic runtime

One pip install. Two sandbox backends. Any data source. Offline. On CPU.

neuralosd is the agentic runtime for neuralOS — the 121M-parameter on-device tool-calling model. It turns any data source into a private, offline question-answering service inside hardware-isolated microVMs.

pip install neuralosd[all]

What it does

YOUR DATA (CSV, DB, API, logs)     THE RUNTIME                THE RESULT
──────────────────────           ──────────────            ──────────────
profile → model → generate  →   @probe + router    →    ask in English,
                         →   chains + guardrails     get verified
                         →   serve + monitor         answers, offline

Two sandbox backends

Backend	Install	Best for
BoxLite	`pip install neuralosd[boxlite]`	persistent service boxes, CoW clones, port publication
Microsandbox	`pip install neuralosd[msb]`	live RAM snapshots, CoW forks, declarative recreate

Both run the same probe contract. Switch by configuration, not code.

Quick start

# 1. Install
pip install neuralosd[all]

# 2. Build an instance from your data
neuralosd build --source your_data.csv --name my-analyst

# 3. Deploy into a sandbox
neuralosd deploy --name my-analyst --backend boxlite

# 4. Ask
neuralosd ask --instance my-analyst "how many records"

The @probe framework

from neuralosd import probe, Instance

@probe(
    description="Customers ranked by lifetime spend",
    triggers=["top customers", "best customers"],
    args={"limit": {"type": "integer", "min": 1, "max": 25, "default": 10}},
    pii=["email"],
)
def top_customers(limit: int = 10):
    return db.query("SELECT ... LIMIT %s", (limit,))

inst = Instance(name="my-analyst", probes=[top_customers])
env = inst.ask("top customers")
print(env["results"])

Chains (multi-step answers)

from neuralosd import chain, ChainRunner

@chain(name="genre_deep_dive", steps=[
    {"probe": "top_genres"},
    {"probe": "tracks_by_genre", "args": {"genre": "{{step_0.genre}}"}},
])
def genre_deep_dive(ctx): ...

runner = ChainRunner(probes_by_name)
runner.register("genre_deep_dive", genre_deep_dive._chain_steps)
result = runner.run("genre_deep_dive")

Meta-selector (multi-instance routing)

from neuralosd import MetaSelector

selector = MetaSelector({
    "finance": {"description": "revenue, invoices, customers"},
    "ops":     {"description": "incidents, uptime, alerts"},
})
instance = selector.route("how many open incidents")  # → "ops"

HITL guardrails

from neuralosd import ConfirmStore
store = ConfirmStore()
pending = store.create(probe_fn, args, reason="low confidence")
# ... human confirms ...
result = store.confirm(pending["confirm_token"])

MCP server (expose probes to any AI agent)

python3 -m neuralosd.mcp /path/to/instance
# or add to Claude Desktop / Cursor MCP config

License

MIT

Metadata

Release files for neuralosd 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for neuralosd 1.0.1
File	Size	Uploaded
neuralosd-1.0.1.tar.gz	29.1 kB	Oct 1, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for neuralosd 1.0.1
File	Interpreter	ABI	Platform	Reset
neuralosd-1.0.1-py3-none-any.whl 32.5 kB Oct 1, 2026	Python 3	none	any	Details

Total release size: 61.6 kB

Release files / neuralosd-1.0.1.tar.gz

Download URL	neuralosd-1.0.1.tar.gz
Size	29.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`c7b9ea52e72cdd216bf987858c21f8398d6f48fb484769bc24e472fa8a34c772`
BLAKE2b-256 checksum How to use checksums	`f8065de13466496f022e8c6b8ff703eedbd685792020c30c38a106bf662ab459`
Upload date	Oct 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.11`

Release files / neuralosd-1.0.1-py3-none-any.whl

Download URL	neuralosd-1.0.1-py3-none-any.whl
Size	32.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`5890393bf97a521920415545ebbbc48278903b8121013c64f0c2c79904185557`
BLAKE2b-256 checksum How to use checksums	`6893aa89e7ff9d7bfe4ab2cdc221b0fe7a3e32ba914dfc9a1b4eccf80b51f3e5`
Upload date	Oct 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.11`