No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is gbrain-evals safe to install? View the security audit →
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 contradicting itself, citing where a fact came from, and staying fast when the brain has hundreds of thousands of pages. And we publish the numbers we are not proud of right next to the ones we are, because a memory system you are going to build on has to be honest about where it is weak. If you are deciding whether to trust gbrain with your agent's memory, this repo is how you check our work instead of taking our word for it. How these benchmarks work (the 60-second version) A benchmark here is three things: A corpus — a pile of realistic content (chat logs, meeting notes, emails, biographical pages). Some is a fictional life we generated; some is a public dataset other researchers use.
| Stars | 428 |
| Forks | 79 |
| Language | TypeScript |
| Category | AI Tool |
| License | MIT |
| Quality Score | 53.2687836020591/100 |
| Open Issues | 8 |
| Last Updated | 2026-10-03 |
| Created | 2026-04-22 |
| Platforms | node |
| Est. Tokens | ~16k |
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.
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
SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
Explore other popular ai tool tools:
gbrain-evals is an open-source ai tool by garrytan with 428 GitHub stars.
gbrain-evals is primarily written in TypeScript.
You can find installation instructions and usage details in the gbrain-evals GitHub repository at github.com/garrytan/gbrain-evals. The project has 428 stars and 79 forks, indicating an active community.
gbrain-evals is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to gbrain-evals on Agent Skills Hub include EDRSilencer, perf-map-agent, shaping-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: