fortifyos-langchain 1.1.0

FortifyOS runtime protection for LangChain and LangGraph agents — zero code changes required.

fortifyos-langchain

Runtime security for LangChain and LangGraph agents — with zero code changes.

fortifyos-langchain auto-attaches the FortifyOS policy engine to every LangChain agent running in your Python environment. It intercepts LLM calls and tool invocations, runs your security policies as plain shell scripts, and allows or blocks the action based on the result.

No imports. No callback wiring. No modifications to your agent code.

Installation

pip install fortifyos-langchain

How It Works

A .pth file shipped with the package is auto-loaded by Python on every interpreter startup, attaching a FortifyHandler globally to LangChain via register_configure_hook. The handler reads ~/.fortifyos/langchain.json to map lifecycle events to shell scripts under ~/.fortifyos/hooks/langchain/.

Event	Fires when
pre_llm	Before an LLM / chat-model call
post_llm	After an LLM responds — includes generations, tool_calls, finish_reason, token_usage
pre_tool	Before a tool runs
post_tool	After a tool returns

Script exit code 0 allows the action; non-zero blocks it.

What's New In 0.1.1

• post_llm payload now includes the actual model output: generations[].text, generations[].content, generations[].tool_calls (the tools the LLM wants to invoke), generations[].finish_reason, token_usage, and model. Useful for inspecting tool calls before they run, detecting content-filter triggers, and tracking token cost.

Disabling Protection

Set FORTIFYOS_DISABLE=1 to skip the auto-attach for a single run.

License

MIT