clampd 0.5.0

Runtime security SDK for AI agents — guard tool calls in 1 line

Clampd Python SDK

Runtime security for AI agents. Guard every tool call — OpenAI, Anthropic, LangChain, Google ADK — in 1 line. Prompt and response scanning enabled by default.

Installation

pip install clampd

With framework extras:

pip install clampd[langchain]    # LangChain callback handler
pip install clampd[mcp]          # MCP server support
pip install clampd[all]          # Everything

Quick Start

import clampd
from openai import OpenAI

# Configure once at startup
clampd.init(
    agent_id="my-agent",
    secret="ags_...",              # from dashboard → Agent → Secret
    gateway_url="http://localhost:8080",
    api_key="ag_live_...",
)

# Wrap your OpenAI client — done
client = clampd.openai(OpenAI())

# Use it exactly like before. Clampd intercepts every tool call.
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Look up active users"}],
    tools=[...],
)
# Dangerous tool calls → blocked before execution
# Safe tool calls → proceed normally
# Prompts scanned before LLM, responses scanned after

What's New in 0.4.0

• scan_input and scan_output now default to True — prompts are scanned before the LLM call, responses are scanned after. Set scan_input=False to opt out.
• 50 detection rules across 20 languages
• 7 compliance frameworks (HIPAA, GDPR, PCI-DSS, CCPA, SOC 2, EU AI Act, NIST AI RMF)

Configuration

Three ways to configure (pick one):

# Option 1: Environment variables
# export CLAMPD_GATEWAY_URL=http://localhost:8080
# export CLAMPD_API_KEY=ag_live_...
# export CLAMPD_AGENT_ID=my-agent
# export JWT_SECRET=ags_...

# Option 2: Global init (recommended)
clampd.init(agent_id="my-agent", secret="ags_...", gateway_url="...", api_key="...")

# Option 3: Inline per-call
@clampd.guard("db.query", agent_id="my-agent", secret="ags_...", gateway_url="...", api_key="...")
def query(sql): ...

Anthropic / Claude

import clampd
from anthropic import Anthropic

clampd.init(agent_id="my-agent", secret="ags_...")
client = clampd.anthropic(Anthropic())

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "..."}],
    tools=[...],
)

LangChain

import clampd

handler = clampd.langchain(agent_id="my-agent", secret="ags_...")

result = executor.invoke(
    {"input": "Look up active users"},
    config={"callbacks": [handler]},
)

Google ADK

import clampd
from google.adk import Agent

agent = Agent(
    tools=[...],
    before_tool_callback=clampd.adk(agent_id="my-agent", secret="ags_..."),
)

Direct Guard (any function)

import clampd

clampd.init(agent_id="my-agent", secret="ags_...")

@clampd.guard("database.query")
def run_query(sql: str):
    return db.execute(sql)

# With response checking (opt-in)
@clampd.guard("file_read", check_response=True)
def read_file(path: str):
    return open(path).read()

run_query("SELECT * FROM users")     # allowed
run_query("DROP TABLE users")        # raises ClampdBlockedError

Scanning Options

# Defaults (v0.4.0+): scan_input=True, scan_output=True
client = clampd.openai(OpenAI(), agent_id="my-agent")

# Opt out of scanning
client = clampd.openai(OpenAI(),
    agent_id="my-agent",
    scan_input=False,   # skip prompt scanning
    scan_output=False,  # skip response scanning
)

Error Handling

from clampd import ClampdBlockedError

try:
    run_query("DROP TABLE users")
except ClampdBlockedError as e:
    print(f"Blocked: {e}")
    # e.risk_score, e.denial_reason, e.request_id

API Reference

Function	Description
clampd.init(...)	Configure global client (once at startup)
clampd.openai(client, **opts)	Wrap OpenAI client (scan_input/scan_output on by default)
clampd.anthropic(client, **opts)	Wrap Anthropic client (scan_input/scan_output on by default)
clampd.guard(tool_name, **opts)	Decorator for any function
clampd.langchain(...)	LangChain callback handler
clampd.adk(...)	Google ADK before_tool_callback

Requirements

• Python 3.10+
• A running Clampd gateway

License

BUSL-1.1