Doberman: The AI watchdog that stops Claude from deleting your database
Details
- External ID
- 49336757
- Source
- HN
- Company
- —
- Product
- database
- Website domain
- github.com
- Launched
- Aug. 17, 2026
- Cohort
- —
- Upvotes
- 9
- Upvotes percentile
- 0.5309139784946236
- Tags
- —
- Fetched at
- Sept. 10, 2026, 5:32 a.m.
- Updated at
- Sept. 10, 2026, 5:32 a.m.
Description
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.
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Security
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- safety guardrails for ai code execution
- Manually corrected
- False
Could you build this?
Yes Doberman is a security wrapper/guardrail proxy for LLM CLI tools and agent tool-calls, which can be implemented by intercepting bash/SQL execution commands and evaluating them via deterministic regex rules and secondary LLM checks.
Discussion
6 comments analyzed.
Competitors mentioned: Claude Code, Cisco Defenseclaw
Concerns raised: Only works with databases, limited scope, Permission creep - agents touching unintended areas, Read-only mode defeats purpose of active agents, Unclear differentiation from other well-funded frameworks
Feature requests: Read-only database user support, Silent/non-intrusive permissions after adaptive learning, Support for frontend, backend, and marketing use cases
Competitors
Other products that read as similar to this one — 37 launches clear the similarity bar, closest 8 shown.
Attention rank: #18 of 38 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 229 days after the earliest competitor.
- Agent-watchdog · ph · 2026-09-21 · 2 upvotes · similarity 0.42
- OpenAPPA · hn · 2026-09-28 · 23 upvotes · similarity 0.40
- jev-guard · github · 2026-09-22 · 7 upvotes · similarity 0.37
- AI Guard · ph · 2026-09-24 · 1 upvotes · similarity 0.36
- Immune-Harness · github · 2026-09-25 · 9 upvotes · similarity 0.36
- GuardRail, shell guards that stop Claude Code before it pushes to main · hn · 2026-09-09 · 5 upvotes · similarity 0.36
- Alovia · ph · 2026-09-29 · 1 upvotes · similarity 0.35
- Latch · hn · 2026-02-06 · 5 upvotes · similarity 0.35
Other launches for this product
- A memory database that forgets, consolidates, and detects contradiction
- Open database of 2k IP camera specs (JSON/CSV, CC0)
- KV and wide-column database with CDN-scale replication
- database
- Connect DuckDB to any database that has an ADBC driver
- Open database of link metadata for large-scale analysis
- Daily-updated database of malicious browser extensions
- I built a database for AI agents
- Open-source Agent in Rust that can't delete your database
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.