HN Explorer

Show HN: Doberman: The AI watchdog that stops Claude from deleting your database (github.com)

2 points by alanfuNZ ↗ HN
Landing Page: https://www.trydoberman.dev/

The Problem: AI guardrails only protect against 89% of dangerous commands. This may seem pretty good until you think of it as a lock that lets 1 in 9 intruders in.

What is Doberman: Doberman is a two layer security system wrapped around your LLM monitoring every input, output and tool call. The first layer is deterministic based on state of the art security guidelines, the second layer is dynamic, learning from your use and personal preferences.

How is Doberman different: It is a dynamic two-layer security system that sits at runtime and monitors every input, output, and tool execution, adapting with you as you work.

7 comments

[ 4.2 ms ] story [ 16.9 ms ] thread
threecheese
Unsure why this feels different from the umpteen other frameworks; maybe it appears to have a human -authored readme, or if it’s just simple enough to fit into my mental model of how agents work.

Whoops, I’ve read too far into the readme. Scratch that first one :)

Anyway, given OP appears to be the author: how are you differentiating from the rest of the (some well funded) guard dogs? The adaptive learning; totp integration; simple tool proxy model; your turn gate state machine’s novelty?

alanfuNZ
Most of the other frameworks sit on the network peremiter and only inspects the prompts. The biggest competition right now that I see in the same lane Cisco's Defenseclaw which focuses on breadth and has relatively loose security guardrails.

Each piece of tech of the framework is not novel, since I'm not trying to reinvent the wheel here. My focus is on the depth of security and a set of invariants that the system is built around. It's designed to be overprotective sitting on the execution path fail closed and raise only. The adaptive learning lowers that security based on your needs so eventually it can become a silent protector that doesn't constantly bother you like CC asking you for permission to do a git push.

alanfuNZ
Also the intro of the readme was written by me, the rest was meant to just be something agents ingest and use to set up Doberman hahaha, didn't think anyone would read the full thing.
sp_25126
This will help many fellow vibe coders
SwtCyber
Give the agent a read-only postgres user. Boom, I just saved you a startup
alanfuNZ
This only works in the case of working with databases, also a lot of the times people are not careful with the permissions that are given to these agents and they oftentimes touch areas that they were not originally meant to touch. For example I use claude code from Frontend UI, to backend development to even marketing. The whole point of agents is that it is active rather than passive, making it read only essentially (imo) defeats the purpose of using an agent in the first place.

I'm not saying we shouldn't have built in precautions and permissions, this should be standard practices, but Doberman is a system built to handle the inevitable case when these precautions fail.