Havuz

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine f

A decision brain for agentic systems: perceive context, compare options, and control execution.

Put your idea on trial in front of a jury of 12 Claudes. A free Claude Code skill.

DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with

A reusable AI skill for stress-testing high-leverage decisions through five strategic lenses.

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.

Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier calibration, SystemOne protocol in

Let Your AI Play Detroit：Become Human

Premortem skill for Claude Code — finds the concrete ways a plan could fail before commitment. Multi-agent silent scan, mitigation triplets,

Make your AI think like Munger, Feynman, or Paul Graham — load real mental models, not personas.

A structured failure-analysis workflow that assumes your plan already failed and works backward to find every reason why. Based on Gary Klei

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.

Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading

🧠 A council of AI models for the decisions that aren't no-brainers — they answer in parallel, debate to consensus, or get judged to a ver

A local CLI for logging predictions before the outcome and checking whether your "80% sure" comes true 80% of the time.

AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk

FALSIFY · 证伪 — 先证伪，再决定。A portable reasoning kernel: evidence layering, falsifiers, and a tamper-evident forecast ledger for any AI agent.

Fork decisions into living simulations with 1,000 personalities. Watch alternate realities diverge and explore second-order effects.

Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing

Transparent randomization tools with fairness receipts, replayable draws, giveaways, tournaments, and live rooms.

Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward p

An AI skill that interrogates you — with your consent — until the story you tell yourself gives way to what's actually true. Claude Code plu

Craft Type-Safe Uncertainty-aware semantic pattern matching, control flow, and smart procedures for Effect DecisionModel and Jev

Agent Skill that checks your big decisions for blind spots against 95 cognitive biases — built from a mental-model lattice.

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text gene

Agent skills built from Algorithms for Decision Making (Kochenderfer, Wheeler & Wray). Expected utility, value of information, bandits, robu

Say 'reflect on <decision>' — your AI runs the decision process of Bezos, Munger & Farnam Street (23 compacted mental models), gives an opin

A methodology so aggressive it demands to be replaced.

Ternary decision scoring with Jevfire-style inference, typed APIs, and reproducible Persian evaluation.

Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, bench