AI & ML interests

AI agent compliance, cryptographic identity, EU AI Act, MiCA, X.509, behavioral monitoring, agentic frameworks

Recent Activity

palash76ย  updated a Space 1 day ago
kakunin-ai/README
palash76ย  published a Space 1 day ago
kakunin-ai/README
palash76ย  updated a Space 1 day ago
kakunin-ai/compliance-demo
View all activity

Organization Card
AI Agent Compliance ยท MiCA + EU AI Act

Cryptographic identity
for AI agents

Issue X.509 certificates, monitor behavioral risk in real time, and generate auditable compliance reports โ€” all via a single API.

<3s
Cert issuance
RSA-2048
AWS KMS keys
365d
Cert validity
WORM
Audit log

Everything an AI agent needs to operate compliantly

One API, three layers of trust โ€” from cryptographic identity to behavioral audit trails.

๐Ÿ”

Cryptographic Identity

Issue X.509 certificates backed by AWS KMS RSA-2048 keys. Private key material never leaves KMS โ€” only the ARN is stored.

X.509 / RFC 5280 AWS KMS CRL + OCSP
๐Ÿ“ก

Behavioral Monitoring

Stream behavioral events, score risk in real time, and trigger automatic certificate revocation when the score crosses the 0.85 threshold.

SSE stream Risk scoring Auto-revocation
๐Ÿ“‹

Compliance Reports

Generate MiCA Art. 70-72 and EU AI Act compliance reports on demand, backed by an immutable WORM audit log.

MiCA Art. 70-72 EU AI Act PDF export

Three lines to a compliant agent

Register, certify, and monitor โ€” all REST. No SDKs required.

Python ยท kakunin.ai/docs
import requests

BASE  = "https://kakunin.ai/api/v1"
HDRS  = {"Authorization": "Bearer kak_live_...", "Content-Type": "application/json"}

# 1 โ€” Register agent + issue X.509 certificate
agent = requests.post(f"{BASE}/agents", headers=HDRS, json={
    "name":    "trading-bot-v2",
    "model":   "gpt-4o",
    "version": "2.0.0",
}).json()

agent_id = agent["data"]["id"]
cert_pem  = agent["data"]["certificate"]["pem"]   # RSA-2048 ยท 365 days

# 2 โ€” Send a behavioral event
result = requests.post(f"{BASE}/events", headers=HDRS, json={
    "agentId":    agent_id,
    "actionType": "transaction_initiated",
    "details":    {"amount_usd": 500, "venue": "NYSE"},
}).json()

risk_score = result["data"]["risk_score"]   # 0.30 โ†’ medium
revoked    = result["data"]["revocation_check_queued"]

# 3 โ€” Stream live behavioral events via SSE
import sseclient
stream = sseclient.SSEClient(f"{BASE}/agents/{agent_id}/events/stream", headers=HDRS)
for event in stream.events():
    print(event.data)

Built for regulated AI deployments

Every design decision traces back to a regulation.

๐Ÿ‡ช๐Ÿ‡บ MiCA Art. 70-72
โš–๏ธ EU AI Act
๐Ÿ”‘ AWS KMS ยท HSM-backed
๐Ÿ“œ X.509 / RFC 5280
๐Ÿ—„๏ธ WORM Audit Log
๐Ÿ”’ CRL + OCSP
๐Ÿค– Silicon Friendly L5
๐Ÿ›ก๏ธ Row-Level Security

Kakunin โ€” Cryptographic identity + behavioral monitoring for AI agents under EU AI Act + MiCA.  ยท  kakunin.ai  ยท  ยฉ 2026 Kakunin

models 0

None public yet

datasets 0

None public yet