Decision Models Python Packages

solvi

A runtime where decision models propose and your code decides: typed questions, hard rules, quotes checked against the text, escalation with a guaranteed error budget, replayable traces. Works with any System One model.

grounded-ai

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

deqio

Run fast, typed AI decision models behind one API. Choice, score and yes/no decisions with multiple engines and hardware backends.

opendxp

NoulXP (formerly OpenDXP): the open standard for System One models. Package an AI decision model once, prove it, calibrate it, run it anywhere over HTTP or MCP.

rlcd-gateway

Self-hosted gateway for LLMs and decision models. Claude Code, Codex, OpenCode and any OpenAI/Anthropic SDK app reach any provider (OpenRouter, Groq, Ollama…) with context pruning; Jev and open-rlcd System One decisions get audit and calibration. Live dashboard, single Go binary.

thinkless

The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.

sys1bench

Benchmark harness for typed System One decision models (choice / score / noul): calibration vs noise floor, framing sensitivity, selective prediction, ordinal fidelity, interference, robustness.

decision-metrics

Traces, metrics, replay, and extensible training datasets for decision models

jev-compatible-server

Open inference runtime for decision models with a Jev-compatible API.

noulxp

NoulXP (formerly OpenDXP): the open standard for System One models. Package an AI decision model once, prove it, calibrate it, run it anywhere over HTTP or MCP.

clef-finetune

Fine-tune Cloudflare's open-source Clef / Clef-flash decision models (LoRA + joint schema head) for vertical decisions like insurance claims and compliance

ex-regex

Match meaning in Python. Find, replace, extract, and compose semantic patterns with typed decisions, explicit uncertainty, and exact replay.

semantic-python

Python, but == can understand meaning—explicitly, inspectably, and safely.