Quality Breakdown
90/ 200
Content Signals
Repo Health
Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.
Trust & Verification
low
Standard permissions only. Safe for general use.
Active
Updated within the last 90 days. Actively maintained.
Risk Assessment
- Repository is a well-known open-source LLM inference project (llama.cpp) by ggml-org
- No evidence of autonomous agent spawning or multi-agent orchestration
- No bootstrap/install scripts requesting elevated system access in root directory
- File list contains standard development configuration (.clang-format, .editorconfig, CMakeLists.txt)
- CI/CD workflows are standard GitHub Actions for building and testing
- CLAUDE.md presence indicates AI tool awareness but no evidence of malicious autonomous behavior requests