Hey everyone,
Like many of you, we got frustrated with the current state of safety guardrails for autonomous agents.
When you're running local LLMs (via Ollama, vLLM, or LM Studio) to execute bash scripts or database queries, calling a remote cloud moderation endpoint (Bedrock, OpenAI Moderation) defeats the entire purpose of running locally:
Instead of asking another model if a proposed command is safe, we built an in-process Abstract Syntax Tree (AST) evaluator that parses Python, SQL, and Bash code blocks directly in caller memory before execution.
If an agent attempts:
rm -rf
, mkfs
, raw device writes)DROP TABLE
, TRUNCATE
)().__class__.__base__.__subclasses__()
)/etc/shadow
, .env
, id_rsa
)The tool execution is aborted in under 40 microseconds (<0.00004s) directly inside Python memory, with zero OS syscalls spawned.
It's published on PyPI as btp-guard
:
bash
pip install btp-guard