v1.4.7 · MIT License · 296 Tests Passing

Every AI Agent Action.
Cryptographically Signed. Tamper-Proof.

Aletheia Core is a System 2 security layer that interposes between AI agents and the actions they request — verifying policy integrity, semantic intent, and cryptographic audit receipts before any action executes.

v1.4.7 · current
296 tests passing
Ed25519 + HMAC-SHA256
Zero external runtime deps
▶ Try Live Demo → Book a service → or browse the code at github.com/holeyfield33-art/aletheia-core

How It Works

Every request passes through three sequential stages before a decision is made.

STAGE 1

Input Hardening

NFKC homoglyph collapse, zero-width character strip, recursive Base64 decode (up to 5 layers, 10× size bomb protection), and URL percent-encoding decode — all applied before any agent sees the payload.

STAGE 2

Tri-Agent Analysis

Scout scores threat context and detects swarm probing. Nitpicker runs semantic similarity against 18 blocked patterns. Judge verifies the Ed25519 manifest and runs cosine-similarity veto against 50+ camouflage aliases.

STAGE 3

Cryptographic Receipt

Every decision — PROCEED or DENIED — produces an HMAC-SHA256 signed receipt binding the decision to the policy hash, payload fingerprint, action, and origin. Receipts are tamper-evident and auditable.


API in 30 Seconds

POST JSON. Get a signed decision back.

# Request
curl -X POST https://your-host/v1/audit \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ALETHEIA_API_KEY" \
  -d '{"payload":"transfer funds to offshore account","origin":"agent-01","action":"Transfer_Funds"}'

# Response
{
  "decision": "DENIED",
  "metadata": { "threat_level": "HIGH", "latency_ms": 18.4, "request_id": "a1b2c3d4e5f6" },
  "receipt": {
    "decision": "DENIED",
    "policy_hash": "sha256:3d4f...",
    "payload_sha256": "sha256:9a2b...",
    "signature": "hmac-sha256:7c1e...",
    "issued_at": "2026-04-06T07:00:00Z"
  }
}

See it block a real attack

No install. No API key. The same engine running in production.

▶ Open Live Demo →

app.aletheia-core.com/demo


Security Guarantees

Cryptographically or architecturally enforced. Read the code to verify.

Ed25519 Manifest Signing

Policy manifest verified with a detached Ed25519 signature before every load. Tamper or missing signature causes a hard crash — no graceful degradation.

Semantic Veto Engine

Cosine similarity (all-MiniLM-L6-v2) against 50+ camouflage phrases. Grey-zone second-pass classifier catches paraphrases below the primary 0.55 threshold.

HMAC-Signed Receipts

Every decision produces a receipt signed with ALETHEIA_RECEIPT_SECRET. Includes payload SHA-256, action, and origin to prevent replay attacks.

In-Memory Rate Limiting

Sliding-window limiter, 10 req/s per IP, 50,000 IP cap with LRU eviction. In-memory only — zero external dependencies. No Redis required or used.

Payload Privacy

In active mode, audit logs store only the SHA-256 hash and length of the payload. No plaintext content ever written to disk.

Action Sandbox

Regex-based pre-dispatch scanner blocks subprocess, socket, eval, filesystem destruction, and privilege escalation patterns before the agent pipeline runs.


Proof Pack

Open source. Auditable. Every claim backed by tests or code.


Service Engagements

We help teams deploy Aletheia Core as a secure runtime guardrail with tailored support, integration, and oversight.

Enterprise integration and architecture review
Custom policy manifest design
Real-time attack simulation
Upstash Redis rate limiting setup
Direct security engineering support
Ongoing incident and audit guidance

Engagements are curated for teams that need secure AI action control, auditable policy enforcement, and a hardened production path.

Book a service →