Typesafe Python Packages

strictyaml

Type-safe YAML parser and validator.

databind

Databind is a library inspired by jackson-databind to de-/serialize Python dataclasses.

databind-core

Databind is a library inspired by jackson-databind to de-/serialize Python dataclasses.

databind-json

Databind is a library inspired by jackson-databind to de-/serialize Python dataclasses.

supercov-cli

Coverage, security and code quality for coding agents

jev-ultralightspeed

BRRRRRRRRRRRRRRRRRRRRRR

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.

jev-ra

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

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.

jevbrief

Clean, traceable state briefings for TypeSafe's Jev model

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

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.

simple-html

fast, templateless html generation

mocksafe

Type-safe mocking for Python.

jevstiller

Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

jev-select

Useful evidence for your AI, within a token budget. A fast, source-linked context selector for files, records, and agents.

pydecide

One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback

agent-alibi

We check whether your agent has an alibi for what it did.

jev-mcp-server

MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.

stuntd

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

jevclient

Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.