Antarraksha AI Agent Enforcement SDK for LangChain
Project description
antarraksha-langchain
Antarraksha AI Agent Enforcement SDK for LangChain.
Installation
pip install antarraksha-langchain
Quick Start
from antarraksha_langchain import AntarakshaCallbackHandler
handler = AntarakshaCallbackHandler(
base_url="https://antarraksha.ai",
agent_id="my-agent",
passport_id="ANTK-PASS-xxx",
)
# Every LLM and tool call is now enforced
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o", callbacks=[handler])
Tool Wrapping
from langchain_community.tools import ShellTool
from antarraksha_langchain import AntarakshaSafeTool, AntarakshaClient
client = AntarakshaClient(agent_id="my-agent", passport_id="ANTK-PASS-xxx")
client.register()
safe_shell = AntarakshaSafeTool(wrapped_tool=ShellTool(), antarraksha_client=client)
# safe_shell.run("ls") — enforced by Antarraksha before execution
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file antarraksha_langchain-0.1.0.tar.gz.
File metadata
- Download URL: antarraksha_langchain-0.1.0.tar.gz
- Upload date:
- Size: 4.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0e15cb1e7f0248503e8b6ab8e1d8458bfc2fdad2528d94fd4a427fe0f31da6ad
|
|
| MD5 |
28e66b867cd85cda5a902bccd26425b9
|
|
| BLAKE2b-256 |
db2cb3dae4d740800e190b5df67a1cc59b7cb1087d0570c477b8bfd442b2a95f
|
File details
Details for the file antarraksha_langchain-0.1.0-py3-none-any.whl.
File metadata
- Download URL: antarraksha_langchain-0.1.0-py3-none-any.whl
- Upload date:
- Size: 5.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
306d05aa55fc5c272ef7cca88fcbf23379a9f8d75464b48aec14d1dd0aeb199c
|
|
| MD5 |
70194c1220383a06c8c5f7fc7af27c41
|
|
| BLAKE2b-256 |
131fd0e6d596af942c49e786a0b0370bf44c91d239f81a26867212b203031091
|