jevmlx — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 bnsd55 · Agent Tool · ★ 69

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is jevmlx safe to install? View the security audit →

About jevmlx

jevmlx Typed decisions from a local model on Apple Silicon. One batched forward pass, every field at once, with a probability per field. Asking an LLM for JSON means parsing what it wrote, fixing what drifted, and retrying until it parses. jevmlx takes a schema of booleans, enums, and multi-selects, scores every allowed answer for every field in one forward pass, and assembles the JSON itself. Nothing is generated token by token: the output is valid by construction and every field carries a probability. Install bash library into your project pip install git+https://github.com/bnsd55/jevmlx CLI only uv tool install git+https://github.com/bnsd55/jevmlx from a clone (dev) git clone https://github.com/bnsd55/jevmlx && cd jevmlx && ./setup.s

apple-siliconjevlocal-llmlocal-modelsmlx

Quick Facts

Stars69
Forks8
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score67.8233791266676/100
Open Issues6
Last Updated2026-09-25
Created2026-09-17
Platformspython
Est. Tokens~15k

Compatible Skills

These tools work well together with jevmlx for enhanced workflows:

  • Rapid-MLX — semantic(0.42)+complementary+shared_fw(ollama,openai)+rare_topics+same_lang+shared_platform (75%)
  • llm_context_benchmarks — semantic(0.21)+complementary+shared_fw(ollama,openai)+same_lang+similar_pop+shared_platform (73%)

jevmlx alternative? Top 6 similar tools

Looking for a jevmlx alternative? If you're comparing jevmlx 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.

  • maclocal-api by scouzi1966 · ⭐ 343

    'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and othe

  • SAM by SyntheticAutonomicMind · ⭐ 130

    Synthetic Autonomic Mind - An AI assistant for everyone.

  • ovo-local-llm by ovoment · ⭐ 105

    A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-devi

  • local-ai-mac by dmitryryabkov · ⭐ 70

    Practical guide to running LLMs locally on Apple Silicon, with a focus on architecture, memory scaling, and a

  • Toolio by OoriData · ⭐ 138

    GenAI & agent toolkit for Apple Silicon Mac, implementing JSON schema-steered structured output (3SO) and tool

  • openjev-sglang by ekzhang · ⭐ 337

    Jev-compatible API endpoint based on open models (prefill-only)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is jevmlx?

jevmlx is Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.. It is categorized as a Agent Tool with 69 GitHub stars.

What programming language is jevmlx written in?

jevmlx is primarily written in Python. It covers topics such as apple-silicon, jev, local-llm.

How do I install or use jevmlx?

You can find installation instructions and usage details in the jevmlx GitHub repository at github.com/bnsd55/jevmlx. The project has 69 stars and 8 forks, indicating an active community.

What license does jevmlx use?

jevmlx is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to jevmlx?

The top alternatives to jevmlx on Agent Skills Hub include maclocal-api, SAM, ovo-local-llm. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools