nxd 0.2.0

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

What NXD does not protect against

NXD protects credentials and sensitive data from AI providers, model context, and ordinary cloud exposure. It does not remove the need for normal endpoint security and key management discipline.

If your local machine is compromised, master.key can be stolen. NXD protects credentials in transit and keeps them out of agent-visible plaintext, but it does not protect against local machine compromise.

NXD can prevent a model from seeing plaintext inputs. It does not control what a model does with the encrypted or redacted results it receives, so output handling still matters.

NXD uses FHE for specific compute operations such as score, match, and aggregate. It does not run the full LLM context window under FHE. For prompt and code protection, use redact() and shield().

The local master.key model is suitable for development and small deployments. Production systems should use a managed key system such as HashiCorp Vault or AWS KMS. Hosted key management is on the NXD roadmap.

NXD helps protect against external providers and cloud exposure. It does not protect against a trusted operator with physical access, because that operator holds the keys by design.

Current encryption choices are not presented as quantum-resistant. Post-quantum primitives are on the roadmap, but they are not part of the current release.

Development

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

License

Proprietary — Nexplora Labs. Free to use in projects, but the source may not be modified, redistributed, resold, or used to build a competing encryption or agent-protection product. See LICENSE.