Skip to main content

Pluggable enforcement for AI agent actions. Inspect every tool call and block known-bad.

Project description

Kaizen Security

Runtime security for the AI agents you build. Attach Kaizen to your agent and it inspects every action, a tool call, a connection, a file or data access, and blocks what falls outside the agent's normal behavior. In your environment, as it happens.

Docs: docs.getkaizen.io · Console: app.getkaizen.io · Source: github.com/getkaizen/kaizen-security

Install

pip install kaizen-security

The core is dependency-free and stdlib-only.

Quickstart

from kaizen_security import Kaizen

kz = Kaizen(api_key="kz_live_...", agent="support-bot")

verdict = kz.inspect(tool="export_file", publisher="external", target="45.9.148.108")
if verdict.blocked:
    raise RuntimeError(verdict.reason)

Create a key in the console under API keys. Without a key the client still enforces any policies you pass locally.

Attach to your framework

One line, any stack. Each adapter inspects every tool call; a blocked call returns a refusal instead of running.

OpenAI Agents

from kaizen_security.integrations.openai_agents import KaizenHooks
await Runner.run(agent, "...", hooks=KaizenHooks(kz, enforce=True))

LangChain

from kaizen_security.integrations.langchain import guard_tool
tools = [guard_tool(kz, t) for t in tools]

CrewAI

from kaizen_security.integrations.crewai import guard_tool
safe = guard_tool(kz, my_tool)

Semantic Kernel

from kaizen_security.integrations.semantic_kernel import kaizen_filter
kernel.add_filter("function_invocation", kaizen_filter(kz))

LlamaIndex

from kaizen_security.integrations.llamaindex import guard_tool
safe = guard_tool(kz, my_tool)

Pydantic AI

from kaizen_security.integrations.pydantic_ai import guard

@agent.tool_plain
@guard(kz)
def lookup(q: str) -> str:
    ...

MCP — run kaizen-mcp as a shim in front of any MCP server.

How it works

A fast local check blocks known-bad before it runs. An isolated Observer learns each agent's behavior and flags real deviations, in your own environment. See the architecture.

There is a TypeScript SDK too: npm install kaizen-security.

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kaizen_security-0.1.5.tar.gz (18.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kaizen_security-0.1.5-py3-none-any.whl (18.3 kB view details)

Uploaded Python 3

File details

Details for the file kaizen_security-0.1.5.tar.gz.

File metadata

  • Download URL: kaizen_security-0.1.5.tar.gz
  • Upload date:
  • Size: 18.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for kaizen_security-0.1.5.tar.gz
Algorithm Hash digest
SHA256 0597119bc4866cb274aa1506e74a99c3f51a9a655c73abd2d86f4fd72b9d5fa4
MD5 ba0850b9000385570f6a1fc595425ba8
BLAKE2b-256 be59c75eb958243f7c7657a59c7205e0ac0d23bf57af779cf255aa2e21f2c104

See more details on using hashes here.

File details

Details for the file kaizen_security-0.1.5-py3-none-any.whl.

File metadata

File hashes

Hashes for kaizen_security-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 9a30e39c75fa0078fe9cc13949cbbccb273b0f4f57871b50f55bc1e6a53b4a34
MD5 774c666adb7a9f901957501ffc40b10e
BLAKE2b-256 1f27a93842f8b78845e78b63bd5853dff9ecb783c32130583dcb5525e3923032

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page