by Szesnasty · Agent Tool · ★ 32
AI Protector Ship AI agents with guardrails — not prayers. For teams shipping tool-calling agents, AI Protector finds prompt injection and unauthorized tool use before production — then enforces policy deterministically, with no LLM in the loop. Find vulnerabilities → add protection → prove the improvement. 📊 [Benchmark matrix → blocked % and latency per
| Stars | 32 |
| Forks | 2 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 66.4588316026854/100 |
| Open Issues | 3 |
| Last Updated | 2026-06-21 |
| Created | 2026-03-02 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with ai-protector for enhanced workflows:
Explore other popular agent tool tools:
ai-protector is Ship AI agents with guardrails — not prayers. Self-hosted runtime protection for LLMs and tool-calling agents: block prompt injection, enforce tool permissions, redact sensitive data, and control what. It is categorized as a Agent Tool with 32 GitHub stars.
ai-protector is primarily written in Python. It covers topics such as agent-security, ai-agents, ai-security.
You can find installation instructions and usage details in the ai-protector GitHub repository at github.com/Szesnasty/ai-protector. The project has 32 stars and 2 forks, indicating an active community.
ai-protector is released under the Apache-2.0 license, making it free to use and modify according to the license terms.