Block unsafe actions before execution. Every decision produces a signed audit receipt for independent verification. Deploy self-hosted or consume as a hosted API.
Every request passes through three sequential stages before a decision is made.
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.
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.
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.
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" } }
No install. No API key required. Send a test payload through a live audit engine and inspect the signed receipt.
▶ Open Live Demo →app.aletheia-core.com/demo
Cryptographically or architecturally enforced. Read the code to verify.
Policy manifest verified with a detached Ed25519 signature before every load. Tamper or missing signature is designed to halt startup — read manifest/signing.py to verify.
Cosine similarity (all-MiniLM-L6-v2) against 50+ camouflage phrases. Grey-zone second-pass classifier catches paraphrases below the primary 0.55 threshold.
Every decision produces a receipt signed with ALETHEIA_RECEIPT_SECRET. Includes payload SHA-256, action, and origin to prevent replay attacks.
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.
In active mode, audit logs are designed to store only the SHA-256 hash and length of the payload — not plaintext content. See core/audit.py.
Regex-based pre-dispatch scanner blocks subprocess, socket, eval, filesystem destruction, and privilege escalation patterns before the agent pipeline runs.
Open source. Auditable. Every claim backed by tests or code.
pytest tests/ -q
secrets.compare_digest — not set membership — to prevent timing oracle attacks on the auth layer.
Clarity on scope prevents integration mistakes and overclaims.
Open-source core. Hosted API launching. Services available now.
MIT-licensed core. Run it yourself. Full source, full control.
Consume Aletheia as a hosted API. No infrastructure to manage.
Self-hosted deployment with support, custom policy design, and SLA options.
Available now. Designed for teams deploying AI agents in production.
Structured review of your agent architecture, action surface, and risk posture. Delivered as a written report with prioritized findings.
Hands-on support deploying Aletheia Core into your stack. Covers policy manifest design, endpoint configuration, and API key setup.
Ongoing monitoring and policy tuning as your agent capabilities evolve. Available as a retainer engagement.
Map your audit receipt outputs to relevant frameworks. Supports documentation for internal controls and third-party reviews.
Full deployment support for private cloud or on-premises environments. Includes architecture review and production readiness checklist.
Half-day or full-day sessions covering AI agent attack vectors, policy design, and incident response playbooks.
info@aletheia-core.com