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 jevk5 safe to install? View the security audit →
JevK5 — an open-weight Jev alternative JevK5 is an independent, Apache-2.0 open-source alternative to TypeSafe's Jev for typed decisions. Give it a state (a ticket, log, policy, or diff) and a yes/no, choice, or score question. It returns a probability for every option in one forward pass, with zero generated tokens. The weights run on your own GPU, and the server accepts the TypeSafe-style request shape. JevK5 is not affiliated with TypeSafe AI. Independent result: JevBench v1.4 ranks JevK5 v0.2 second of 76 systems and first among open entrants (62.04; Jev 1.13.0: 63.29). On its 308 fresh sealed decisions, JevK5 answered 33.1% correctly and Jev answered 36.7%; the evaluator calls this set unusually difficult. The ranking measures JevBench's mix of accuracy, calibration, speed, and cost, not performance on every production workflow. JevK5's reported H100 latency is about 13 ms for short decisions. Watch it run Typed decision on an NVIDIA L40S. A real support ticket becomes a probability over three teams; the displayed decision took 20.60 ms after model loading. This is a paced replay of recorded GPU output. Click the moving preview for the full 27-second video.
| Stars | 132 |
| Forks | 10 |
| Language | Python |
| Category | AI Tool |
| License | Apache-2.0 |
| Quality Score | 64.6671066730939/100 |
| Open Issues | 5 |
| Last Updated | 2026-09-28 |
| Created | 2026-09-22 |
| Platforms | python |
| Est. Tokens | ~15k |
These tools work well together with jevk5 for enhanced workflows:
Looking for a jevk5 alternative? If you're comparing jevk5 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.
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisio
1207 public resources for Jev, TypeSafe AI's System One decision model, indexed by decision pattern. Source ci
🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System On
🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub
A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runti
Explore other popular ai tool tools:
jevk5 is JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.. It is categorized as a AI Tool with 132 GitHub stars.
jevk5 is primarily written in Python. It covers topics such as calibration, decision-model, jev.
You can find installation instructions and usage details in the jevk5 GitHub repository at github.com/allebee/jevk5. The project has 132 stars and 10 forks, indicating an active community.
jevk5 is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to jevk5 on Agent Skills Hub include open-alternative-jev, awesome-jev, awesome-jev-gallery. 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: