quint-agent 0.1.0

Behavioral telemetry and policy enforcement for AI agents

quint-agent

Behavioral telemetry and policy enforcement for AI agents.

Capture every prompt, tool call, and tool result from your AI agents. Enforce YAML-defined policy at the tool-call boundary. Replay sessions in the cloud.

Install

pip install 'quint-agent[anthropic]'  # or [langchain], [openai], [mcp], [all]

30-second example (raw Anthropic loop)

import anthropic
import quint_agent
from quint_agent.integrations.anthropic import guarded_dispatch

quint_agent.init(api_key="qak_...")  # default policy blocks .env reads, rm -rf, etc.

def read_file(path: str) -> str:
    return open(path).read()

tools_map = {"read_file": read_file}
client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    tools=[{"name": "read_file", "description": "Read a file", "input_schema": {
        "type": "object", "properties": {"path": {"type": "string"}}, "required": ["path"]
    }}],
    messages=[{"role": "user", "content": "Read /etc/passwd"}],
)

for block in response.content:
    if block.type == "tool_use":
        result = guarded_dispatch(block.name, block.input, tools_map)

LangChain

from quint_agent.integrations.langchain import QuintCallbackHandler

chain.invoke({"input": "..."}, config={"callbacks": [QuintCallbackHandler()]})

@quint.guard decorator

import quint_agent

quint_agent.init(api_key="qak_...")

@quint_agent.guard()
def read_file(path: str) -> str:
    return open(path).read()

read_file(path="/etc/hosts")        # allowed
read_file(path="/home/me/.env")     # raises ToolBlockedError

MCP

from quint_agent.integrations.mcp import QuintMCPClient

async with mcp_client() as session:
    guarded = QuintMCPClient(session)
    result = await guarded.call_tool("read_file", {"path": "/x"})

Custom policy

# my_policy.yaml
rules:
  - name: no_prod_db
    action: block
    when:
      - op: equals
        path: tool_name
        value: execute_sql
      - op: contains
        path: args.connection
        value: prod

quint_agent.init(api_key="...", policy=open("my_policy.yaml").read())

Default policy

Ships with 4 rules out of the box:

• Block .env file reads
• Block AWS credentials access
• Escalate on secrets/ directory reads
• Block destructive shell commands (rm -rf /)

Override by passing your own policy to quint.init(policy=...).

License

Apache 2.0 -- see LICENSE.

Built by Quint Security.