Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/garrytan/gbrain-evals.git
Taken from the project's README on GitHub. Check the security audit before running it.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 501 |
| Forks | 86 |
| Language | TypeScript |
| Category | AI Tool |
| License | MIT |
| Quality Score | 53/100 |
| Open Issues | 37 |
| Last Updated | 2026-11-19 |
| Created | 2026-04-22 |
| Platforms | node |
| Est. Tokens | ~16k |
gbrain-evals The test suite for gbrain, the long-term memory an AI agent reads from and writes to. Everything here is public, runs on your own machine, and can be reproduced from a commit hash. We test the whole surface that an agent's memory has to get right, not just the one number that looks good in a tweet: finding the relevant thing, remembering who's who, keeping time straight, not...
Looking for a gbrain-evals alternative? If you're comparing gbrain-evals with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
All powerful skills of ClaudeKit.cc!
A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from report
A java agent to generate method mappings to use with the linux `perf` tool
Skills I use with Claude for shaping
A tool to make socks connections through HTTP agents
Open-source AI research assistant for biomedicine — chat to run RNA-seq, drug discovery, clinical analysis, an
Explore other popular ai tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: