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 →
by kshetrajna12 · AI Tool · ★ 82
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is reflex safe to install? View the security audit →
reflex A tiny "decision model" you can run on your own GPU. You give it some information (a support ticket, a document, a photo) and a list of questions with fixed answer options. It answers all the questions at once and tells you how sure it is about each option, as percentages. It never writes free text, so it can never make up an answer that isn't on your list. It is an open re-creation of Jev, the "System One" model TypeSafe released in September 2026, built on top of a normal open-weights model (Qwen3.5-4B by default). That whole answer comes back in about 100 ms once the state is cached. Your code then decides what to do with the numbers ("auto-route if above 90 %, otherwise ask a human"). Try it in your browser first https://kshetrajna12.github.io/reflex/ runs the whole thing on your own GPU through WebGPU (Chrome, Edge, or Safari 18+) with a 650 MB Qwen3.5-0.8B model. Pick a preset, load the model once, drop in a photo, press Run. Nothing is uploaded anywhere. It is the same request format and the same readout
| Stars | 82 |
| Forks | 8 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 59.5733421371264/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-20 |
| Created | 2026-09-17 |
| Platforms | python |
| Est. Tokens | ~15k |
These tools work well together with reflex for enhanced workflows:
Looking for a reflex alternative? If you're comparing reflex with other ai tool tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights
Skill to talk to Claude about your projects over the phone
.NET MAUI skills for GitHub Copilot and Claude Code
Explore other popular ai tool tools:
reflex is A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.. It is categorized as a AI Tool with 82 GitHub stars.
reflex is primarily written in Python.
You can find installation instructions and usage details in the reflex GitHub repository at github.com/kshetrajna12/reflex. The project has 82 stars and 8 forks, indicating an active community.
reflex is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to reflex on Agent Skills Hub include redesigned-pancake, claude-code-voice-skill, maui-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: