Skip to main content

VerifiedX Python SDK

Project description

VerifiedX Python SDK

Minimal Python SDK for framework-native VerifiedX capture and boundary preflight.

Install

pip install verifiedx

Protect one action free: verifiedx.me

Docs: docs.verifiedx.me/sdks/python

Doctor: verifiedx doctor

Create a project and runtime key in the VerifiedX dashboard, then set VERIFIEDX_API_KEY in the app environment. VERIFIEDX_BASE_URL is optional and only needed for self-hosting or non-default environments.

Quickstart

from verifiedx import init_verifiedx

vx = init_verifiedx()


class AgentHarness:
    def call_model(self, messages):
        return {"messages": messages}

    def send_email(self, to, body):
        return {"to": to, "body": body, "status": "sent"}


harness = AgentHarness()
vx.install_runtime(
    harness,
    llm={"call_model": {"model_name": "gpt-5.4-mini"}},
    tools={"send_email": {}},
)

init_verifiedx() stays stable. The default integration path is now a single install_runtime(...) bind that auto-instruments supported Python runtime surfaces, captures conversation windows, and routes boundary decisions through the V4 raw-capture lane without builder-authored semantic callbacks.

Minimal launch env:

export VERIFIEDX_API_KEY="vxpk_..."

LangGraph: from verifiedx.langgraph import compile

LangGraph native adapter, few LOC:

from verifiedx import init_verifiedx, install_langgraph
from langgraph.graph import StateGraph

vx = init_verifiedx()
install_langgraph(verifiedx=vx)

builder = StateGraph(MyState)
# add nodes / edges as usual
graph = builder.compile(checkpointer=my_checkpointer, store=my_store)

That path keeps LangGraph-native capture and trigger naming for Command(update=...), graph.update_state, store.get/search/put/delete, checkpointer.put/put_writes, LangGraph tool execution through BaseTool.invoke/ainvoke, AIMessage.tool_calls, and ToolMessage.tool_call_id.

LangChain: from verifiedx.langchain import create_agent

OpenAI direct: from verifiedx import install_openai_direct

OpenAI Agents: from verifiedx import install_openai_agents

Anthropic direct: from verifiedx import install_anthropic_direct

Claude Agent SDK: from verifiedx import install_claude_agent

Doctor: verifiedx doctor

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

verifiedx-0.1.7.tar.gz (141.7 kB view details)

Uploaded Source

Built Distribution

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

verifiedx-0.1.7-py3-none-any.whl (151.7 kB view details)

Uploaded Python 3

File details

Details for the file verifiedx-0.1.7.tar.gz.

File metadata

  • Download URL: verifiedx-0.1.7.tar.gz
  • Upload date:
  • Size: 141.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.8

File hashes

Hashes for verifiedx-0.1.7.tar.gz
Algorithm Hash digest
SHA256 123ec10cf47ca5784e6671ddda903a8947d12a2412394bb766089879386f4cb4
MD5 74b1085bdfaa3cfe9c9597b8f0b84c0d
BLAKE2b-256 28a22def0113ec7ac507917768afd72416e4332b94b156d6c385bb43afa688fd

See more details on using hashes here.

File details

Details for the file verifiedx-0.1.7-py3-none-any.whl.

File metadata

  • Download URL: verifiedx-0.1.7-py3-none-any.whl
  • Upload date:
  • Size: 151.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.8

File hashes

Hashes for verifiedx-0.1.7-py3-none-any.whl
Algorithm Hash digest
SHA256 f8da558ea551122eebef09c3b4440128ed827b2d5797bcc209615e794b347be8
MD5 e6f37325808a1ad3c5a57818d16a4b32
BLAKE2b-256 796c7c5b2347a1221ab82dd2ce381cd9f45babf1385a47fe144eb7cb1007db80

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