Mental Models GitHub

Open source · MIT · MCP-ready

The Mental Models Latticework

A multidisciplinary open-source decision-support system and AI reasoning engine. 50 foundational models synthesized across physics, economics, evolutionary biology, and cognition.

0+
Models
0
Disciplines
0
Latticework connections
0
Anki cards
0%
Free & open source

Problem-to-Model Engine

Describe the dilemma. Get the triad.

A primary lens, the model that compounds it, and the counter-balance that keeps it from becoming dogma. Same matcher as `mm diagnose` in the CLI; the quick picks are hand-curated.

The Library

Fifty models, eight disciplines, one latticework.

Every model ships with a diagnostic checklist, three case studies, its failure modes, its neighbours in the lattice and a reasoning protocol for AI agents.

Core Thinkingchestertons-fence

Chesterton's Fence

Do not remove a fence until you know why it was put there.

The principle that reforms, deletions, or removals of existing structures, rules, or code should never be made until the underlying rationale for why they were established in the first place is thoroughly understood.

Deleting legacy codeOverhauling organizational processes
View playbook & checklist
Core Thinkingcircle-of-competence

Circle of Competence

Knowing what you don't know is more useful than being brilliant.

The practice of identifying the realistic boundaries of your genuine knowledge and expertise, ruthlessly operating within that boundary, and avoiding the illusion of skill outside of it.

Entering unfamiliar marketsEvaluating advice from charismatic…
View playbook & checklist
Core Thinkingfalsifiability

Falsifiability

A statement is scientific if and only if it is falsifiable.

The principle that for any hypothesis, theory, or statement to be considered genuinely scientific or predictive, it must be capable of being proven empirically false through observable evidence.

Evaluating unfalsifiable corporate strategies…Designing rigorous A/B tests and production…
View playbook & checklist
Core Thinkingfirst-principles

First-Principles Thinking

I know of no other way of thinking than starting with the fundamentals and reasoning up from there.

The practice of deconstructing a problem down to its most fundamental, irreducible truths and building up a solution from scratch, rather than reasoning by analogy.

Facing deeply entrenched legacy assumptions…Seeking 10x breakthrough innovation or…
View playbook & checklist
Core Thinkinghanlons-razor

Hanlon's Razor

Never attribute to malice that which is adequately explained by stupidity.

Never attribute to malice that which is adequately explained by carelessness, ignorance, incompetence, or cognitive overload.

Interpersonal conflictUnexplained API breakages
View playbook & checklist
Core Thinkinginversion

Inversion

Invert, always invert: Turn a situation or problem upside down. What happens if all our plans go wrong?

The practice of approaching problems backwards, focusing on avoiding failure, catastrophe, and stupidity rather than striving for brilliant success.

Complex projects with high downside risk and…direct forward planning feels opaque
View playbook & checklist
Core Thinkingmap-vs-territory

Map vs. Territory

The map is not the territory.

The fundamental realization that an abstraction, model, diagram, or metric of reality is not the reality itself, and that confusing the two leads to catastrophic misjudgment.

Relying exclusively on dashboardsDisconnect between executive strategy decks…
View playbook & checklist
Core Thinkingoccams-razor

Occam's Razor

Entities should not be multiplied beyond necessity.

Among competing hypotheses or design solutions that predict or achieve identical outcomes, the one requiring the fewest assumptions and simplest components should be selected.

Over-engineered software architectures and…Debugging root causes in complex
View playbook & checklist
Core Thinkingproximate-vs-root-cause

Proximate vs. Root Cause

For want of a nail the shoe was lost. For want of a shoe the horse was lost. For want of a horse the rider was lost. For want of a rider the message was lost. For want of a message the kingdom was lost.

The crucial distinction between the immediate, surface event that triggered a failure (proximate cause) and the deeper, systemic condition or structural vulnerability that allowed the failure to occur (root cause).

Incident post-mortems and blameless…Medical diagnostics
View playbook & checklist
Core Thinkingsecond-order-thinking

Second-Order Thinking

And then what?

The discipline of evaluating decisions not just by their immediate, intended consequences, but by the subsequent ripple effects and non-linear reactions that follow.

Policy changesRefactoring core system interfaces with…
View playbook & checklist
Core Thinkingsteelmanning

Steelmanning (The Principle of Charity)

You are not entitled to an opinion on something unless you can state the arguments against your position better than the smartest people who disagree with you.

The practice of constructing the strongest, most compelling possible version of your opponent's or alternative's argument before attempting to critique, refute, or dismiss it.

Technical design reviews and architectural…Evaluating competitive threats or disruptive…
View playbook & checklist
Core Thinkingthought-experiments

Thought Experiments (Gedankenexperiment)

Imagination is more important than knowledge. For knowledge is limited, whereas imagination embraces the entire world.

The practice of exploring the implications of an idea, hypothesis, or paradox using pure disciplined mental visualization when physical empirical experimentation is impossible or prohibitively costly.

Exploring unprecedented future scenarios or…Testing ethical boundaries
View playbook & checklist
Economics & Strategyasymmetric-payoffs

Asymmetric Payoffs

Look for situations where you can lose 1x your investment if you are wrong, but can gain 10x, 50x, or 100x if you are right.

Situations where the potential upside of an action or investment dwarfs the strictly capped, finite downside, creating an overwhelmingly favorable risk-reward profile.

Making seed investmentsEvaluating speculative initiatives with fixed…
View playbook & checklist
Economics & Strategycomparative-advantage

Comparative Advantage & Specialization

Even if you are the fastest typist in the world, if you are also a \$1,000/hour corporate litigator, you should hire a secretary to type your legal briefs.

The economic principle that individuals, teams, or nations maximize collective and personal prosperity by specializing in producing the goods or services for which they have the lowest opportunity cost, and trading for everything else, even if one party possesses an absolute advantage in every single task.

Delegating workBuild vs buy decisions for internal software…
View playbook & checklist
Economics & Strategyeconomic-moats

Economic Moats & Competitive Defensibility

A truly great business must have an enduring 'moat' that protects excellent returns on invested capital.

The structural, sustainable competitive advantages that protect a business or platform from competitor encroachment, allowing it to generate superior returns on invested capital over decades.

Evaluating competitive advantages of a new…Analyzing pricing power and margin…
View playbook & checklist
Economics & Strategynash-equilibrium

Nash Equilibrium & Prisoner's Dilemma

A Nash Equilibrium is when everyone is making the best decision they can, taking into account everyone else's decision—even when everyone ends up miserable.

A state in a game or competitive system where no player has an incentive to unilaterally change their chosen strategy, even if the resulting mutual equilibrium is sub-optimal or destructive for everyone involved.

Price warsStandards wars
View playbook & checklist
Economics & Strategynetwork-effects

Network Effects

The value of a telecommunications network is proportional to the square of the number of connected users of the system ($n^2$).

The economic dynamic where a product, platform, or service becomes exponentially more valuable to existing and prospective users as more participants join and utilize the network.

Designing platformsEvaluating sustainable competitive moats and…
View playbook & checklist
Economics & Strategyopportunity-cost

Opportunity Cost

The cost of anything is the amount of life you exchange for it.

The true cost of any choice is not merely the financial outlay, but the lost value of the next best alternative that must be forgone as a consequence.

Budgeting engineering timeSaying "yes" to low-impact commitments or…
View playbook & checklist
Economics & Strategyprincipal-agent-problem

Principal-Agent Problem

Show me the incentive, and I will show you the outcome.

The structural conflict of interest that arises when one party (the agent) is authorized to make decisions on behalf of another party (the principal), but the agent's personal incentives and risks do not align with those of the principal.

Designing employee compensationHiring external contractors
View playbook & checklist
Economics & Strategysunk-cost-fallacy

Sunk Cost Fallacy

When you find yourself in a hole, stop digging.

The irrational cognitive bias of continuing an endeavor or allocating further resources based on the accumulated historical investments (time, money, effort) that can never be recovered, rather than evaluating forward expected value from the current baseline.

Lingering on failing software rewrites or…Reluctance to terminate unprofitable client…
View playbook & checklist
Evolution & Biologynatural-selection

Natural Selection & Survival of the Fittest

It is not the strongest of the species that survives, nor the most intelligent that survives. It is the one that is most adaptable to change.

The universal process where differential reproductive success driven by environmental selection pressure acts upon heritable variation, causing adaptive traits to proliferate and maladaptive traits to be eliminated over generations.

Designing evolutionary software algorithms…Market competition
View playbook & checklist
Evolution & Biologyred-queen-effect

The Red Queen Effect

Now, here, you see, it takes all the running you can do, to keep in the same place. If you want to get somewhere else, you must run at least twice as fast as that!

The principle that in a co-evolving, competitive system, continuous adaptation, innovation, and exertion are required simply to maintain one's current relative standing and avoid extinction.

Rapidly shifting competitive landscapesStaying relevant in an evolving professional…
View playbook & checklist
Evolution & Biologysignaling-theory

Costly Signaling & The Handicap Principle

A signal is reliable only if it is too expensive for a fraud to fake.

The principle that for a signal or communication to be credible and trusted between actors with conflicting incentives, it must be inherently costly, difficult to fake, or impose a genuine handicap on the sender.

Evaluating credentialsAnalyzing brand advertising
View playbook & checklist
Operations & Strategydefense-in-depth

Defense in Depth

Never rely on a single wall to protect the kingdom. Layer the moat, the outer wall, the inner keep, and the citadel.

The strategy of employing multiple layered, independent, and redundant defensive controls so that the failure or compromise of any single protective barrier does not result in total system breach or catastrophic collapse.

Designing cybersecurity architecture and…Nuclear power safety
View playbook & checklist
Operations & Strategyfog-of-war

The Fog of War & Epistemic Uncertainty

War is the realm of uncertainty; three quarters of the factors on which action is based are wrapped in a fog of greater or lesser uncertainty.

The profound uncertainty, ambiguity, misinformation, and cognitive confusion that invariably characterizes real-time operations, live incidents, and high-stakes conflict.

Live production outagesNegotiating complex deals where…
View playbook & checklist
Operations & Strategyooda-loop

The OODA Loop

He who can handle the quickest rate of change survives.

A four-step decision cycle (Observe, Orient, Decide, Act) emphasizing that the competitor or system capable of processing and resetting the loop faster and more accurately dictates the conflict and causes adversary collapse.

Fast-paced competitive environmentsOperating under imperfect information and…
View playbook & checklist
Physics & Engineeringactivation-energy

Activation Energy & Catalysts

A match generates heat only after you strike it hard enough to overcome the friction threshold.

The initial threshold of energy required to initiate a chemical, physical, or behavioral process that, once overcome, allows the reaction to proceed spontaneously or release net positive energy.

User onboarding frictionProcrastination
View playbook & checklist
Physics & Engineeringcritical-mass

Critical Mass

Below critical mass, the reaction fizzles and dies. Above critical mass, it becomes self-sustaining and unstoppable.

The minimum amount of concentrated material, energy, or participation required to sustain a self-propagating chain reaction without dying out.

Bootstrapping two-sided marketplaces and…Launching viral marketing campaigns and…
View playbook & checklist
Physics & Engineeringentropy

Thermodynamics & Entropy

The second law of thermodynamics is, without a doubt, one of the most inviolable laws of nature: left to themselves, things always tend to go from order to disorder.

The fundamental physical law that in any isolated system, disorder, noise, and randomness tend naturally to increase over time, and that maintaining structure, order, and functionality requires the continuous expenditure of external energy.

Codebase rotOrganizational decay
View playbook & checklist
Physics & Engineeringleverage

Leverage (Physical & Conceptual)

Give me a lever long enough and a fulcrum on which to place it, and I shall move the world.

The principle where a small initial input force or asset applied at an advantageous pivot point (fulcrum) produces an outsized, amplified output effect.

Capital allocationAutomating manual engineering workflows and…
View playbook & checklist
Physics & Engineeringmargin-of-safety

Margin of Safety

You don't drive a 9,800-pound truck across a bridge built to hold exactly 10,000 pounds. You build a bridge that holds 30,000 pounds.

The practice of intentionally designing excess buffer capacity into a system, bridge, calculation, or financial allocation to absorb unexpected stress, variance, human error, and unknown unknowns.

Sizing cloud infrastructureFinancial runway planning
View playbook & checklist
Probability & Mathbase-rate-fallacy

Base Rate Fallacy

When you hear hoofbeats, think horses, not zebras.

The cognitive tendency to ignore general prior statistical distribution rates in favor of specific, vivid, but unrepresentative descriptive anecdotes or test results.

Evaluating medical screening tests or fraud…Assessing startup success probabilities or…
View playbook & checklist
Probability & Mathcompounding

Compounding & Exponential Growth

Compound interest is the eighth wonder of the world. He who understands it, earns it; he who doesn't, pays it.

The mathematical process where the returns, gains, or outputs of an asset, knowledge base, or habit are reinvested to generate their own additional returns, resulting in explosive, non-linear growth over long time horizons.

Long-term financial planningBuilding technical skills
View playbook & checklist
Probability & Mathergodicity

Ergodicity & Absorbing Barriers

In an ergodic system, the average of one person over time equals the average of many people at one point in time. Real life is almost never ergodic.

The critical distinction between the average outcome of a group across parallel worlds (ensemble average) and the average outcome of a single individual operating sequentially over time (time average).

Decisions involving existential riskHigh-leverage financial investments and…
View playbook & checklist
Probability & Mathexpected-value

Expected Value

Take the probability of loss times the amount of possible loss from the probability of gain times the amount of possible gain. That is what we're trying to do.

The anticipated value of an investment, decision, or action calculated by multiplying each possible outcome by its mathematical probability and summing the results.

High-stakes betsMaking decisions under uncertainty where…
View playbook & checklist
Probability & Mathpower-laws-pareto

Power Laws & The Pareto Principle (80/20)

In the real world, things do not follow polite bell curves. A tiny handful of events dictate the entire distribution.

The mathematical relationship where a tiny percentage of participants, causes, or inputs account for a vastly disproportionate majority of the outputs, wealth, or consequences, following a scale-free fat-tailed distribution.

Venture capital portfoliosSoftware bug triage
View playbook & checklist
Probability & Mathregression-to-the-mean

Regression to the Mean

Extreme outcomes are inevitably followed by more moderate ones, not because of intervention, but because of statistics.

The statistical phenomenon that if an extreme, outlier measurement or performance is observed on a first trial, subsequent measurements will tend naturally to be closer to the historical average simply due to the reversion of random chance.

Evaluating extreme employee performance reviewsSports magazine cover jinxes
View playbook & checklist
Probability & Mathsurvivorship-bias

Survivorship Bias

Look for the missing bullet holes.

The logical error of focusing exclusively on the successful "survivors" of a selective process while completely ignoring the failures and dropouts who were eliminated along the way, leading to dangerously distorted conclusions.

Analyzing advice from billionaire college…Upgrading system components based only on…
View playbook & checklist
Psychology & Cognitionanchoring-bias

Anchoring & Adjustment

The first number placed on the table exerts a gravitational pull on all subsequent thinking.

The cognitive bias where an individual relies excessively on the first piece of information encountered (the "anchor") when making subsequent estimations or decisions, making insufficient adjustments away from that initial reference point.

Price negotiationsSoftware engineering sprint estimates and…
View playbook & checklist
Psychology & Cognitionavailability-heuristic

Availability Heuristic

If you can think of it easily, it must be important.

The mental shortcut where people evaluate the frequency, probability, or importance of an event based on how easily concrete, vivid examples of it come to mind.

Overreacting to recent dramatic news eventsEstimating software architecture risks based…
View playbook & checklist
Psychology & Cognitionconfirmation-bias

Confirmation Bias

What the human being is best at doing is interpreting all new information so that their prior conclusions remain intact.

The pervasive psychological tendency to search for, interpret, favor, and recall information in a way that confirms one's preexisting beliefs or hypotheses, while systematically ignoring or dismissing contradictory evidence.

Technical debatesValidating user research and product-market…
View playbook & checklist
Psychology & Cognitionloss-aversion

Loss Aversion

Losses loom larger than gains.

The psychological phenomenon where the pain of losing something is cognitively experienced as roughly twice as intense as the pleasure of gaining an equivalent amount.

Reluctance to cut losses on failing projectsUser behavior in freemium conversions
View playbook & checklist
Psychology & Cognitionsocial-proof

Social Proof & Informational Cascades

When people are free to do as they please, they usually imitate each other.

The psychological phenomenon where people assume the actions, beliefs, and behaviors of others in an attempt to reflect correct behavior in a given, ambiguous situation.

Designing landing pagesAssessing irrational market bubbles
View playbook & checklist
Systems & Complexityantifragility

Antifragility

Some things benefit from shocks; they thrive and grow when exposed to volatility, randomness, disorder, and stressors.

The property of systems that increase in capability, resilience, or robustness as a consequence of stressors, volatility, noise, mistakes, faults, attacks, or failures.

Designing systems operating in highly…Portfolio construction
View playbook & checklist
Systems & Complexityemergence

Emergence & Self-Organization

The whole is greater than the sum of its parts.

The phenomenon where a collection of simple agents interacting according to basic local rules gives rise to complex, unpredictable, macroscopic properties and behaviors that cannot be found in any individual component.

Designing distributed architecturesExplaining sudden systemic cultural shifts
View playbook & checklist
Systems & Complexityfeedback-loops

Feedback Loops (Reinforcing & Balancing)

You cannot understand a system simply by looking at its parts; you must look at how the outputs of the parts circulate back to influence their own causes.

The circular causality where the output of a system circles back to either amplify (reinforcing) or stabilize (balancing) the initial input, driving exponential change or equilibrium.

Viral growthRegulating temperature
View playbook & checklist
Systems & Complexitygalls-law

Gall's Law

A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works and cannot be patched to make it work. You have to start over with a working simple system.

The rule of thumb that a complex system that works is invariably found to have evolved from a simple system that worked; conversely, a complex system designed from scratch never works and cannot be patched to make it work.

Big-bang legacy system rewrites and…Designing brand-new enterprise workflows or…
View playbook & checklist
Systems & Complexitygoodharts-law

Goodhart's Law

When a measure becomes a target, it ceases to be a good measure.

When a measure becomes a target, it ceases to be a good measure, because actors will optimize to maximize the target while corrupting the underlying process it was intended to represent.

Setting KPIsMonitoring developer productivity metrics
View playbook & checklist
Systems & Complexitytheory-of-constraints

Theory of Constraints

A chain is no stronger than its weakest link. Any improvement not made at the constraint is an illusion.

The principle that any manageable system is limited in achieving more of its goals by a very small number of constraints (typically just one at any given time), and that any improvement made outside of that bottleneck is an illusion.

Optimizing workflowsResolving chronic delivery delays and…
View playbook & checklist
Systems & Complexitytragedy-of-the-commons

Tragedy of the Commons

Freedom in a commons brings ruin to all.

The systemic dilemma where individuals acting independently and rationally according to their own self-interest deplete, degrade, or destroy a shared, finite common-pool resource, even when it is clear that doing so is contrary to the collective's long-term survival.

Shared cloud computing infrastructure with…Depletion of open-source maintainer bandwidth…
View playbook & checklist

The Latticework Graph

No model works alone.

50 nodes, 140 connections. Solid lines pair models that compound each other; dashed lines mark counter-balances. Hover to isolate a neighbourhood, click to open the playbook.

Core ThinkingSystems & ComplexityProbability & MathEconomics & StrategyEvolution & BiologyPsychology & CognitionPhysics & EngineeringOperations & Strategy paired counter

Developer & AI Tooling

Same library, four interfaces.

The Markdown files are the single source of truth. The CLI, the MCP server, the agent skill and the Anki deck are all generated from them, with zero external dependencies.

Model Context Protocol

Claude Desktop, Claude Code, Cursor, Antigravity

Clone the repo, then register the stdio server. The agent gets list_mental_models, get_mental_model, search_mental_models and diagnose_dilemma as tools.

{
  "mcpServers": {
    "mental-models": {
      "command": "python3",
      "args": ["/path/to/mental-models/mcp/server.py"]
    }
  }
}

Agent skill

Multi-model cross-examination before a refactor or a strategic call

Read SKILL.md

The skill at skills/mental-models/SKILL.md tells an agent when to consult the library and how to structure a Mental Models Evaluation: situational diagnosis, cross-examination with a counter-perspective, a concrete checklist and a prescribed action. Copy the folder into your agent's skills directory (for Claude Code, ~/.claude/skills/) or point the agent at the repo.

Terminal CLI

Python 3, standard library only

git clone https://github.com/gabrielrondon/mental-models.git && cd mental-models
./cli/mm diagnose "We want to rewrite a legacy billing module"
./cli/mm show chestertons-fence
./cli/mm search "uncertainty"
./cli/mm random

Anki deck

100 flashcards, two per model

Download TSV

One card for the core mechanism, one for the diagnostic playbook. Import in Anki with File → Import, field separator Tab, and “Allow HTML in fields” enabled. Regenerate any time with python3 scripts/export_anki.py.