Doberman is an open-source, runtime security layer for AI coding agents. It sits between the agent and its tools and gives every action a PASS, AUTH or BLOCK verdict before it runs. A deterministic core catches known dangerous behavior, while an adaptive layer learns whatβs normal for you and raises risk when something looks off. It fails closed and learning is raise-only. Works with Claude Code, Codex, OpenClaw and MCP clients like Cursor.
Developer ToolsArtificial IntelligenceGitHubSecurity








Advertisement (Responsive)
π¬ Comments
π Details
Launched
September 1, 2026
Upvotes
5
Comments
1
Source
Public data
Advertisement (Responsive)






This tool has 1 comments on Product Hunt.
View comments on Product Hunt β