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 Shanghua-Gao · Agent Tool · ★ 57
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is RSI-Jev safe to install? View the security audit →
RSI-Jev A recursively self-improving research system that builds Jev-style System One models. AI agents propose the hypotheses, register their predictions before spending GPU time, run the experiments, and retire their own champions when the evidence says to. Ask one of these models a typed question about a document — yes/no, pick-one-of-k, rate-on-a-rubric — and a single forward pass returns a probability for every option instead of prose. Nothing is generated, so another decision about a document already read costs about 10 ms. The loop running the research is the next version of AutoScientists. Want to collaborate, or support the work with compute or funding? Reach out to Shanghua Gao. RSI process <img src="assets/loop-social.gif" width="900" alt="Above: six turns of the cycle climb to v1.0 and the champion line rises with them, then twenty-four directions press against that line without crossing it. Below: one experiment travels propose, experiment, learn; at the gate nearly all become
| Stars | 57 |
| Forks | 4 |
| Language | HTML |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 61.7934213284927/100 |
| Last Updated | 2026-10-03 |
| Created | 2026-09-22 |
| Est. Tokens | ~18k |
Looking for a RSI-Jev alternative? If you're comparing RSI-Jev with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of pros
Typed decisions with TypeSafe's Jev, the first System One model
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast
Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only
JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotic
Explore other popular agent tool tools:
RSI-Jev is Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.. It is categorized as a Agent Tool with 57 GitHub stars.
RSI-Jev is primarily written in HTML. It covers topics such as ai-agents, autonomous-research, decision-model.
You can find installation instructions and usage details in the RSI-Jev GitHub repository at github.com/Shanghua-Gao/RSI-Jev. The project has 57 stars and 4 forks, indicating an active community.
RSI-Jev is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to RSI-Jev on Agent Skills Hub include jevcore, awesome-jev-typesafe, awesome-jev. 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: