ciphyrs 2.5.0

Python SDK for the Ciphyrs PII Shield API

Ciphyrs — PII Shield for AI Workflows

Intercept, mask, and restore PII before it reaches any LLM. Works with LangChain, CrewAI, or any Python application.

Install

pip install ciphyrs                  # core SDK
pip install 'ciphyrs[langchain]'     # + LangChain integration
pip install 'ciphyrs[crewai]'        # + CrewAI integration
pip install 'ciphyrs[all]'           # everything

Quick Start

from ciphyrs import CiphyrsClient

client = CiphyrsClient(
    api_key="cyp_live_...",
    base_url="https://www.ciphyrs.com"
)

# Mask PII
result = client.mask("Contact Praveen at 9876125640 and [e-mail]")
print(result.masked_text)
# "Contact XXXX_a1b2c3 at XXXX_d4e5f6 and XXXX_g7h8i9"

# Restore PII
restored = client.restore(result.masked_text, result.session_id)
print(restored.restored_text)
# "Contact Praveen at 9876125640 and [e-mail]"

One-Shot Protect (recommended)

protect() wraps mask → LLM call → restore so you can't accidentally ship [PERSON_1] to end users:

from openai import OpenAI
oai = OpenAI()

result = client.protect(
    user_message,
    lambda masked, ctx: oai.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": masked}],
    ).choices[0].message.content,
)
return result["output"]    # "Hello John, ..." — never "[PERSON_1]"

Active Blocking — Guard (V58)

Inline <50ms allow/block decision, 5 detection layers:

# Option 1 — manual check
guard = client.guard_check(input=user_msg, agent_name="support-bot")
if guard["decision"] == "block":
    return {"error": guard["reason"]}, 400

# Option 2 — full wrap
result = client.guard_wrap(user_msg, lambda inp:
    oai.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": inp}],
    ).choices[0].message.content
)
if result["blocked"]:
    return {"error": result["reason"]}, 400
return {"reply": result["output"]}

Security Operations (V55-V59)

# List recent attacks
detections = client.list_detections(days=7, severity="high")

# Plant a honeypot canary
created = client.create_canary(name="fake-admin-secret", scope="output")
print(created["token"])   # save this; plant it where it shouldn't appear

# Generate compliance evidence PDF
report = client.generate_prod_report(
    title="Q4 SOC 2 Evidence",
    range_start="2026-10-01",
    range_end="2026-12-31",
    sections=["security_incidents", "pii_detections", "performance", "cost"],
)
pdf_bytes = client.download_prod_report_pdf(report["report"]["id"])
open("soc2-evidence.pdf", "wb").write(pdf_bytes)

# Share with auditors (no login required)
share = client.share_prod_report(report["report"]["id"], ttl_days=30)
print(share["share_url_path"])

Authentication

All API calls require an x-api-key header. Get your API key from the Ciphyrs Dashboard.

1. Register at ciphyrs.com/register
2. Go to Settings > API Keys
3. Click Generate API Key
4. Copy the key (starts with cyp_live_)

LangChain Integration

Option 1: Callback Handler (auto-masks all LLM calls)

from langchain_openai import ChatOpenAI
from ciphyrs.integrations.langchain import CiphyrsPIICallback

callback = CiphyrsPIICallback(api_key="cyp_live_...")
llm = ChatOpenAI(model="gpt-4o", callbacks=[callback])

# PII is automatically masked before reaching OpenAI
# and restored in the response
result = llm.invoke("Hi, I'm Praveen Kumar, my phone is 9876125640")

Option 2: LCEL Runnables (pipe operator)

from ciphyrs.integrations.langchain import CiphyrsMaskRunnable, CiphyrsRestoreRunnable

session = {}
mask = CiphyrsMaskRunnable(api_key="cyp_live_...", session_store=session)
restore = CiphyrsRestoreRunnable(api_key="cyp_live_...", session_store=session)

# Build pipeline: mask -> prompt -> llm -> restore
chain = mask | prompt_template | llm | restore
result = chain.invoke({"input": "Call Praveen at 9876125640"})

Option 3: Shield Wrapper (wrap any chain)

from ciphyrs.integrations.langchain import CiphyrsShield

shield = CiphyrsShield(api_key="cyp_live_...")
safe_chain = shield.wrap(my_existing_chain)
result = safe_chain.invoke({"input": "Praveen's email is [e-mail]"})

Async Support

from ciphyrs import AsyncCiphyrsClient

async with AsyncCiphyrsClient(api_key="cyp_live_...") as client:
    result = await client.mask("Contact Praveen at [e-mail]")
    restored = await client.restore(result.masked_text, result.session_id)

Detected Entity Types

Entity	Example
PERSON	Praveen Kumar
EMAIL	[e-mail]
PHONE	9876125640
IN_AADHAAR	2345 6789 0123
IN_PAN	ABCDE1234F
CREDIT_CARD	4111-1111-1111-1111
IP_ADDRESS	192.168.1.1
DATE_OF_BIRTH	15/03/1990
LOCATION	Mumbai
ORGANIZATION	Acme Corp
API_KEY	sk-abc123...

Links

• Website
• Documentation
• Dashboard