Built a zero-latency AST bouncer for local agent tool-calling

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:

It adds 1,500ms–2,500ms of cloud latency to every single tool invocation.

It breaks the air-gap / local privacy guarantee.

Built a zero-latency AST bouncer for local agent tool-calling

Related reading

Tool Gating for AI Agents

Stop Using LLMs to Audit Other LLMs: You Are Bricking Your Production Latency

Building with Local LLMs: An Engineer's Approach to AI-Assisted Development

I’m building a local-first TypeScript guard for runaway AI-agent costs

The Local AI Assistant Trap: Why Running Your Own Costs More Than You Think

Agentic AI Security: Sandboxing LLM Tool Calls in Production