nxd 0.3.7

Encrypted compute layer for AI agents

NXD 0.3.7

NXD is an encrypted compute layer for AI agents. It wraps fully homomorphic encryption, credential vaulting, privacy primitives, and operator-only reveal flows 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 - when shield() is used for full payload encryption. vault.safe_use() prevents credential leakage from callbacks. redact() reduces PII exposure but is not a guarantee wall.
3. The operator holds the keys - keys stay local, auditable, and revocable.

Install

export NXD_OPERATOR_PASSPHRASE="NXD-2026-Nexplora-Secure!"
pip install nxd==0.3.7

Requires Python 3.10 or 3.11 for the FHE path (concrete-ml).

Passphrase Requirements

NXD_OPERATOR_PASSPHRASE must be:

• At least 12 characters
• A mix of letters, numbers, and symbols
• Not a common word or phrase

Strong example: NXD-2026-Nexplora-Secure!

Weak examples rejected at startup: nexplora2026, password123

Your vault security depends entirely on passphrase strength. A weak passphrase is vulnerable to offline dictionary attacks if the vault files are obtained.

Quick start

import nxd

# 1. Shield code before any AI call
code = "api_key = 'sk_live_xxxx'"
shielded = nxd.shield(code)
recovered = nxd.unshield(shielded)
print(f"AI sees:  {shielded[:40]}...")
print(f"You see:  {recovered}")
print(f"Match:    {code == recovered}")

# 2. Redact PII before sending to AI
note = "Patient John Smith, DOB 1985-04-12, SSN 432-11-5678"
clean, mapping = nxd.redact(note)
print(f"\nAI gets:  {clean}")
print(f"Original: {nxd.deredact(clean, mapping)}")

# 3. Vault a credential and use it without returning it
vault = nxd.Vault(agent_id="my-agent")
vault.store("stripe_key", "sk_live_xxxx")
result = vault.safe_use(
    "stripe_key",
    lambda key: {"status": "charged", "auth_len": len(key)},
)
print(f"\nAgent got: {result}")
print("Key seen:  never")

# 4. Verify tamper-proof audit chain
nxd.audit.log("session", agent_id="my-agent")
print(f"\nAudit valid: {nxd.audit.verify()}")

Redaction

redact() returns both the safe text and the local restoration mapping:

import nxd

safe, mapping = nxd.redact("Patient John Smith, SSN 432-11-5678")
restored = nxd.deredact(safe, mapping)
print(safe)
print(restored)

redact() catches common PII and secret formats including emails, phone numbers, SSNs, many API key families, bearer tokens, physician names, dates, and account numbers.

Important: redact() is pattern-based detection. It reduces exposure, but it is not a guaranteed wall. For complete payload protection, combine it with shield().

Security Model

Memory Safety

NXD provides SecureString for credential handling and secure_store() for best-effort zeroing after storage.

import nxd

vault = nxd.Vault(agent_id="memory-safe")

with nxd.SecureString("sk_live_xxxx") as secret:
    vault.store("api_key", secret.read())

credential = bytearray(b"sk_live_buffered_secret")
vault.secure_store("buffered_key", credential)
print(vault.use("api_key", lambda value: len(value)))

Honest caveat: Python string interning and garbage collection mean zero-on-delete is best-effort, not guaranteed. The strongest protection is to avoid loading secrets into Python strings at all:

import os
import nxd

vault = nxd.Vault(agent_id="env-pop")
os.environ["API_KEY"] = "sk_live_env_secret"
vault.store("api_key", os.environ.pop("API_KEY"))
print("API_KEY" in os.environ)

Callback Safety

Use safe_use() in production to detect accidental credential leakage in callback return values.

import nxd

vault = nxd.Vault(agent_id="callback-safe")
vault.store("stripe_key", "sk_live_xxxx")

try:
    vault.safe_use("stripe_key", lambda key: {"status": "ok", "key": key})
except nxd.CredentialLeakError as exc:
    print(type(exc).__name__)

result = vault.safe_use(
    "stripe_key",
    lambda key: {"status": "charged", "auth_len": len(key)},
)
print(result)

use() still exists when you need callback flexibility, but callbacks must use credentials, not return them.

Audit Integrity

The audit chain is protected against:

• Entry modification via HMAC-signed entries
• Entry injection via sequential hash verification
• Entry reordering via chained previous-hash checks
• Entry truncation via a signed manifest with entry count and tail hash

If the manifest is lost, recover it explicitly:

import nxd

nxd.audit.log("example", agent_id="recover-demo")
print(nxd.audit.verify())
print(nxd.audit.recover())
print(nxd.audit.verify())

CLI equivalent:

nxd audit-recover

Back up ~/.nxd/ regularly. Losing master.key means losing access to vaulted data.

Import Surface

import nxd

with nxd.SecureString("sk_live_xxxx") as secret:
    vault = nxd.Vault(agent_id="imports")
    vault.store("key", secret.read())

vault.secure_store("key", bytearray(b"sk_live_buffer"))
vault.safe_use("key", lambda credential: {"status": "ok", "len": len(credential)})

print(nxd.CredentialLeakError.__name__)
print(nxd.VaultError.__name__)
print(nxd.audit.recover())

Handoff tokens

Handoff tokens are single-use. A token that has already been unpacked raises ReplayError if it is unpacked again.

import nxd

handoff = nxd.Handoff()
token = handoff.pack({"client": "Jane Doe", "balance": 50000})
payload = handoff.unpack(token)
print(payload)

For multi-agent workflows where the same context is needed by multiple agents, pack a separate token for each agent.

Audit export

import nxd

nxd.audit.log("docs-example", agent_id="my-agent")
nxd.audit.export("audit_report.json")
print("export works")

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	96/96 passed	python3 prove.py
Real-world simulation	34/34 passed	python3 realworld.py
Pytest suite	62 passed	pytest -q

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.

• Local machine compromise still defeats local key custody. master.key lives on your machine. If your machine is compromised, keys are at risk. Hosted key management is planned for v0.4.0.
• split() and blur() are pending external cryptographic review. All other primitives wrap vetted libraries such as Fernet, Ed25519, PBKDF2, and Concrete ML.
• redact() remains best-effort pattern detection. It catches many common formats, but unusual or context-dependent secrets can still be missed.
• SecureString and secure_store() are best-effort mitigations inside CPython. Python string interning and garbage collection mean the strongest protection is still to avoid creating long-lived plaintext strings in the first place.
• NXD uses FHE for specific compute operations such as score, match, and aggregate. It does not run the full LLM context window under FHE.
• NXD 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 not part of the current release.

Operator workflow

Set NXD_OPERATOR_PASSPHRASE before using the vault, audit chain, signatures, or any operator-only reveal flow. NXD stores ciphertext at rest, and local key files are wrapped with a PBKDF2-derived key from that operator passphrase.

When you use nxd init, NXD can vault .env secrets, replace them with NXD_VAULT::NAME references, and write an encrypted .env.backup.nxd recovery file.

On the MCP path, decrypt-style tools such as nxd_unshield, nxd_unseal_text, and nxd_detokenize no longer return plaintext to the agent. They queue an operator-only reveal:

nxd reveal <reveal_id>

Roadmap

v0.3.x shipped

• Agent vault isolation
• Concurrent vault safety
• Passphrase strength enforcement
• API key redaction coverage
• Audit truncation detection
• Uniform VaultError messages
• SecureString memory-safety helpers
• safe_use() callback leak detection
• Audit manifest recovery

v0.4.0

• Hosted key management (HashiCorp Vault, AWS KMS)
• nxd.Vault(hosted=True)

v0.5.0

• External cryptographic audit of split() and blur()
• Formal security certification

v0.6.0

• Hardware-accelerated FHE on GPU/TPU
• Sub-10 ms encrypted inference

Development

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