Metadata-Version: 2.4
Name: iris-security-langchain
Version: 0.2.1
Summary: IRIS governance for LangChain agents — Cedar policy on every tool call
Author-email: IRIS Platform <sdk@iris.ai>
License: Apache-2.0
Project-URL: Homepage, https://iris-security.github.io/iris-sdk/
Project-URL: Repository, https://github.com/IRIS-Security/iris-sdk
Project-URL: Documentation, https://iris-security.github.io/iris-sdk/getting-started.html
Project-URL: Issues, https://github.com/IRIS-Security/iris-sdk/issues
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: iris-security-core>=0.1.18
Requires-Dist: iris-security-sdk>=0.2.18
Provides-Extra: langchain
Requires-Dist: langchain>=0.2; extra == "langchain"
Requires-Dist: langchain-core>=0.2; extra == "langchain"
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
Requires-Dist: ruff>=0.4; extra == "dev"

# iris-langchain

IRIS governance for LangChain agents. Add Cedar policy enforcement and evidence logging in three lines — no agent rewrite required.

```python
from iris_langchain import IrisLangChainAgent
from iris import AgentPassport, ComplianceTag

passport = AgentPassport(
    name="support-agent",
    owner="team@company.com",
    compliance_tags=[ComplianceTag.COLORADO_AI_ACT],
    is_high_risk_ai=True,
)
agent = IrisLangChainAgent.from_agent(base_agent, passport)
result = agent.run("Help this customer with their account")
```

See `examples/governed_agent.py` for a full agent setup.
