jeff — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 logan-markewich · AI Tool · ★ 148

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

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

About jeff

jeff A self-hosted implementation of TypeSafe's jev System One API, powered by GLiFormer (400M parameters). Use the official by pointing at jeff. Supports (pick an option), (rate on ordered levels), and (probability of yes). Cheaper to self-host, but less accurate than jev on reasoning-heavy tasks. See benchmarks. Quickstart · Deploy · Configuration · API · Development Quickstart Requires uv and Python 3.12. Run from the repository root: Serves at . Device selection: CUDA → MPS → CPU. The sync above also installs . Save this as : python from typesafesdk import Choice, Noul, Score, TypeSafeClient client = TypeSafeClient(apikey="devkey", baseurl="http://localhost:8000") result = client.systemone( "I was charged twice. Please help ASAP.", { "billing": Noul(instructions="Is this about billing?"), "tone": Choice( instructions="What is the tone?", criteria={"calm": None, "angry": "hostile"}, ), "urgency": Score(

classificationencoderglinerjevtypesafe

Quick Facts

Stars148
Forks7
LanguagePython
CategoryAI Tool
LicenseMIT
Quality Score71.5407501860854/100
Last Updated2026-09-20
Created2026-09-19
Platformspython
Est. Tokens~15k

Compatible Skills

These tools work well together with jeff for enhanced workflows:

  • jev-codex-router — semantic(0.42)+complementary+rare_topics+same_lang+similar_pop+shared_platform (69%)

jeff alternative? Top 6 similar tools

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

  • awesome-jev-by-typesafe by Anil-matcha · ⭐ 667

    Evidence-backed use cases, patterns, prompts, and starter code for TypeSafe Jev — a System One model for fast,

  • awesome-typesafe by AbdelStark · ⭐ 372

    A curated list of official resources and community projects for TypeSafe, System One models, and Jev.

  • jev-align by sutro-sh · ⭐ 205

    Build calibrated AI classifiers from human feedback using Jev and GEPA.

  • openJev-verdict-2.0 by Heman10x-NGU · ⭐ 133

    Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (

  • pi-jev by y0usaf · ⭐ 106

    TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, ca

  • awesome-jev by AnotiaWang · ⭐ 96

    A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources.

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is jeff?

jeff is A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.. It is categorized as a AI Tool with 148 GitHub stars.

What programming language is jeff written in?

jeff is primarily written in Python. It covers topics such as classification, encoder, gliner.

How do I install or use jeff?

You can find installation instructions and usage details in the jeff GitHub repository at github.com/logan-markewich/jeff. The project has 148 stars and 7 forks, indicating an active community.

What license does jeff use?

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

What are the best alternatives to jeff?

The top alternatives to jeff on Agent Skills Hub include awesome-jev-by-typesafe, awesome-typesafe, jev-align. 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 AI Tool tools