Jev Python Packages

pygpt-net

Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - chat, agents, tools, MCP, plugins, RAG, vision, voice, image and video generation, speech synthesis and speech recognition, web search, memory, presets, canvas, assistants, themes, computer use. Windows, Linux, and Mac.

supercov-cli

Coverage, security and code quality for coding agents

prompture

Prompture is an API-first library for requesting structured JSON output from LLMs (or any structure), validating it against a schema, and running comparative tests between models.

jev-ultralightspeed

BRRRRRRRRRRRRRRRRRRRRRR

typellm

TypeLLM: LLMs with type-safe generation

von-sdk

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

jevals

Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

jevnav

Page truth for browser agents — and decisions that replay, test and audit. Jev picks the element, risky actions are gated, every run replays offline in CI.

hunch-jev

Ask Jev over columns of data: closed-set questions, cached and joined back.

jev-ra

Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.

docseek

Goal-driven document discovery: give it a website and a goal in plain language, get back the documents with relevance verdicts.

semantic-operators

An abstraction for System One models, currently supporting TypeSafe's Jev and Laya. Typed questions, probabilities, and "don't know" instead of a guess, from Python, the command line, or MCP

gutfeel

Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.

jigor

zero-shot classifier models gateway and runner

jevbrief

Clean, traceable state briefings for TypeSafe's Jev model

grounded-ai

Evals that meet you where you are. For AI that's grounded.

jev-sort

sort by meaning: order lines along a plain-English dimension, from pairwise comparisons judged by TypeSafe's Jev model

jev-cli

Small dependency-free CLI for TypeSafe Jev

jevkit-runtime

Shared Python infrastructure for the JevKit tools

house-party-protocol

A local harness for agent teams on Claude Code and Codex CLI: only what they prove counts as done. Waves and lanes split the work, reviewers from another model family judge it, councils keep the dissent that lost, typed decisions with Jev are measured before they are trusted, and approvals are bound to the bytes they approved. No model calls.

anyjev

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

jev-grep

grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.

jevcompass

Tool and skill suggestions for Codex Desktop and CLI, with local-first privacy and optional Jev ranking

edgejev

离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev