nxd 0.1.0

Encrypted compute layer for AI agents

NXD

NXD is an encrypted compute layer for AI agents. It wraps fully homomorphic encryption, credential vaulting, and privacy primitives behind a single Python import — so developers can run agents on sensitive data without exposing client records, credentials, or proprietary code to models, clouds, or MCP servers.

Three guarantees

1. The agent works fully — capability unchanged; scores, matches, charges, and aggregates complete normally.
2. The agent sees nothing — sensitive values stay encrypted; agents handle opaque tokens and references only.
3. The operator holds the keys — keys stay local, auditable, and revocable.

Install

pip install nxd

Requires Python 3.10 or 3.11 (Concrete ML FHE dependency).

Quick start

import nxd

# FHE compute on encrypted data
results = nxd.score(model, clients)
matched  = nxd.match(model, record_a, record_b)
average  = nxd.aggregate(model, records)

# Credentials — agent never sees plaintext keys
vault = nxd.Vault(agent_id="billing-agent")
vault.store("stripe_key", "sk_live_xxxx")
result = vault.use("stripe_key", stripe_charge_fn)
vault.audit_log()

# Agent-to-agent encrypted context
handoff = nxd.Handoff()
token = handoff.pack(clients)
scores = nxd.receive(model, token, handoff)

# Code and text privacy before any AI call
protected = nxd.shield(source_code)
original = nxd.unshield(protected)

# Encrypted search, identity, tokenization, PII redaction
index = nxd.build_index(records)
token, hits = nxd.search(index, "diabetes")
nxd.register("user_123", "credential")
nxd.verify("user_123", candidate)
safe = nxd.redact("Patient John Smith, SSN 432-12-6789")
token = nxd.tokenize("4532-1234-5678-9010")

# Documents, channels, state, signatures
nxd.seal("contract.pdf")
ch = nxd.channel("agent-a", "agent-b")
nxd.checkpoint.save("agent-123", state)
nxd.sign("agent-a", "approve payment")

# Privacy analytics, key control, audit
nxd.blur(47230.0, sensitivity=1000, epsilon=1.0)
shares = nxd.split("master_key", n=5, m=3)
locked = nxd.bind(data, recipient="agent-compliance-7")
nxd.audit.verify()

Benchmarks (MacBook Air, Python 3.11, Concrete ML 1.9.0)

Operation	Latency	Notes
FHE score (1 record)	~183 ms	First-call cold start
FHE score (1k records, parallel)	1.6 s	8 cores, ~1.6 ms/record
FHE match (single pair)	352 ms	Cross-system comparison
FHE aggregate (1k records, parallel)	1.8 s	~0.009% quantization error
Credential vault use	<1 ms	Decrypt in memory only
Proof suite	85/85 passed	python3 prove.py

Development

git clone https://github.com/Nexploraai/nxd
cd nxd
pip install -e ".[dev]"
python3 prove.py
python3 agent.py
python3 demo.py

License

MIT — see LICENSE.