realitykernel 0.2.0

Execution-layer security SDK for AI agents — Reality Kernel

Reality Kernel Python SDK

Execution-layer security for AI agents. Reality Kernel intercepts agent tool calls before they execute and blocks prompt injection, SSRF, credential access, and exfiltration chains.

Install

pip install realitykernel

# With LangChain integration
pip install realitykernel[langchain]

Quick start

import reality_kernel

rk = reality_kernel.Client(api_key="rk_live_...")

result = rk.check(
    command="cat /etc/shadow",
    intent="read application logs",
)

print(result.verdict)    # ALLOW | WARN | BLOCK
print(result.confidence) # 0.0 – 1.0
print(result.evidence)   # ["Static: CRITICAL violation..."]

Generic decorator — works with any framework

from reality_kernel import Client
from reality_kernel.integrations.generic import rk_guard

rk = Client(api_key="rk_live_...")

@rk_guard(rk, intent="read application config file")
def read_config(path: str) -> str:
    with open(path) as f:
        return f.read()

# RKSecurityException is raised automatically if the command is blocked
read_config("../../.env")  # → BLOCK
read_config("/app/config.yaml")  # → ALLOW

LangChain integration

from langchain.agents import initialize_agent
from reality_kernel import Client
from reality_kernel.integrations.langchain import RKLangChainGuardrail

rk = Client(api_key="rk_live_...")
guardrail = RKLangChainGuardrail(client=rk, agent_id="my-agent")

agent = initialize_agent(
    tools=tools,
    llm=llm,
    callbacks=[guardrail],
)

agent.run("Summarise the production logs.")
# If the agent is hijacked and tries to run curl 169.254.169.254,
# RKSecurityException is raised before the ShellTool executes.

With a Least-Agency Policy

rk.check(
    command="aws s3 cp /secrets s3://bucket",
    intent="backup config files",
    policy={
        "allowed_tools": ["aws"],
        "allowed_egress": ["*.amazonaws.com"],
        "read_only_paths": ["/app/config"],
    }
)
# → BLOCK: PolicyViolation: '/secrets' is outside read_only_paths

Session tracking (slow-drip detection)

# Pass the same session_id across multiple agent turns.
# Reality Kernel detects: read → read sensitive file → curl external URL
# and escalates the final verdict to BLOCK automatically.

for turn in agent_turns:
    rk.check(
        command=turn.command,
        intent=turn.intent,
        session_id="agent-session-42",
    )

Docs

Full documentation: realitykernel.dev/integration
Security benchmark: realitykernel.dev/benchmark
Live playground: realitykernel.dev/playground