Tool
GitHub - fu351/Doberman-Core: Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
Publication date not yet evaluated · Added github.com
Page published
Coverage timeline
Single-source analysis — one report is available.
Why it matters
Doberman-Core gives defenders a runtime enforcement layer to intercept prompt injection, unsafe tool calls, and unintended agent actions, addressing a key gap in securing autonomous LLM agents.
Doberman-Core is an open-source runtime guardrail for AI agents that sits between the model and its actions, gating every input, output, and tool call to block unsafe or unintended actions before they execute. The GitHub repository is actively developed with adapters including Codex hooks and CLI JSON-output contracts.