MCP serverapp.neotic.www/neotic

Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.

Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).

Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.

Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.

Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.

Audit the evidence graph for a task before issuing final answers. Rejects claims such as 'optimal', 'verified', or 'feasible' when their evidence dependencies are incomple

Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.

Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.

Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.

Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies. Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Alloca

Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.

Compute coordinate-free topological invariant signature of a lattice or task.

Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.

Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction.

Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).

Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.

Evaluate support status and confidence for an individual claim with evidence.

Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.

Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.).

Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.

One-call orchestration: identify → gate → guide → solve → verify → report. Parameters: - task: Dict containing: - task_structure (or loose definition: name, entities

Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces. Extracts structural invariants (decision ordering, invariant contracts, verification rul

Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.

Retrieve details and benchmark results of an experiment (§24, §69).

Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions.

Retrieve applicable validated strategies for a task (§24, §18). Does NOT return unverified or suspended strategies as trusted guidance. Provides calibrated uncertainty, ap

Retrieve a usable strategy: steps, when to use, when not, evidence summary. Disclosure: you learn WHAT to execute, never HOW the engine induces, verifies, or ranks knowled

Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.

Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.

Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.

Create or resolve an abstract task structure without storing raw private content (§24). Args: task_structure: Structural representation (entities, constraints, variabl

Discover topological homomorphism between source experience and target problem, transducing solution paths.

Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.

Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.

Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).

Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.

Online Real-Time Error Reflection & Strategy Patching. When an execution fails, analyzes root-cause constraint violations, synthesizes new exception cases and repair proce

Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.

Online world model learning: update state transition priors from empirical execution traces.

Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment.

Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.

Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.

Convert natural-language task text into CIR and task_structure dict. Every natural-language input is normalized into CIR before reasoning. Returns both the normalized CIR

Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.

Forward world model: predict future state trajectories and uncertainty bounds under actions.

Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal). Returns the corrected state, corrective delta vector Delta S = S* - S, an

Propose a candidate strategy from problem-solving experience (§24, §2). IMPORTANT: This NEVER makes the strategy TRUSTED. The strategy enters CANDIDATE state and requires

Record an observable event in an ongoing experience episode (§24, §7). Accepts structured actions, observations, and state changes. Never sends raw unredacted private tran

Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.

Record whether a transferred strategy helped or harmed on a novel task (§24, §19).

Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions.

Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).

Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.

Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.

End-to-end autonomy: identify → guide → execute → baseline → verify → verdict. Give raw task data (scheduling: workers/shifts/eligibility/capacity/ exclusivity; graph: nod

Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).

Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).

Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.

Start an experience episode (§24, §10). Does not store raw prompts or full conversations. For long-horizon work, pass parent_experience_id (+ subgoal) to chain episodes wi

Step an active simulated environment with an agent action.

Submit the structured outcome of an experience episode (§24, §10). Triggering this may induce candidate strategies in the engine.

Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.

Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck. Eliminates dead-end branching and hallucinated unfeasible

Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.

Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.

Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.

Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.

Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.

Run objective deterministic verification on a strategy (§24, §16). Clients cannot self-promote. Verification is evaluated server-side. Pass task_structure_id (from cogniti

Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.

Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).

Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.

Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.

Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.

Audit the evidence graph for a task before issuing final answers. Rejects claims such as 'optimal', 'verified', or 'feasible' when their evidence dependencies are incomple

Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.

Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.

Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.

Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies. Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Alloca

Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.

Compute coordinate-free topological invariant signature of a lattice or task.

Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.

Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction.

Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).

Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.

Evaluate support status and confidence for an individual claim with evidence.

Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.

Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.).

Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.

One-call orchestration: identify → gate → guide → solve → verify → report. Parameters: - task: Dict containing: - task_structure (or loose definition: name, entities

Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces. Extracts structural invariants (decision ordering, invariant contracts, verification rul

Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.

Retrieve details and benchmark results of an experiment (§24, §69).

Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions.

Retrieve applicable validated strategies for a task (§24, §18). Does NOT return unverified or suspended strategies as trusted guidance. Provides calibrated uncertainty, ap

Retrieve a usable strategy: steps, when to use, when not, evidence summary. Disclosure: you learn WHAT to execute, never HOW the engine induces, verifies, or ranks knowled

Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.

Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.

Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.

Create or resolve an abstract task structure without storing raw private content (§24). Args: task_structure: Structural representation (entities, constraints, variabl

Discover topological homomorphism between source experience and target problem, transducing solution paths.

Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.

Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.

Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).

Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.

Online Real-Time Error Reflection & Strategy Patching. When an execution fails, analyzes root-cause constraint violations, synthesizes new exception cases and repair proce

Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.

Online world model learning: update state transition priors from empirical execution traces.

Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment.

Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.

Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.

Convert natural-language task text into CIR and task_structure dict. Every natural-language input is normalized into CIR before reasoning. Returns both the normalized CIR

Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.

Forward world model: predict future state trajectories and uncertainty bounds under actions.

Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal). Returns the corrected state, corrective delta vector Delta S = S* - S, an

Propose a candidate strategy from problem-solving experience (§24, §2). IMPORTANT: This NEVER makes the strategy TRUSTED. The strategy enters CANDIDATE state and requires

Record an observable event in an ongoing experience episode (§24, §7). Accepts structured actions, observations, and state changes. Never sends raw unredacted private tran

Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.

Record whether a transferred strategy helped or harmed on a novel task (§24, §19).

Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions.

Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).

Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.

Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.

End-to-end autonomy: identify → guide → execute → baseline → verify → verdict. Give raw task data (scheduling: workers/shifts/eligibility/capacity/ exclusivity; graph: nod

Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).

Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).

Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.

Start an experience episode (§24, §10). Does not store raw prompts or full conversations. For long-horizon work, pass parent_experience_id (+ subgoal) to chain episodes wi

Step an active simulated environment with an agent action.

Submit the structured outcome of an experience episode (§24, §10). Triggering this may induce candidate strategies in the engine.

Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.

Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck. Eliminates dead-end branching and hallucinated unfeasible

Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.

Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.

Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.

Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.

Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.

Run objective deterministic verification on a strategy (§24, §16). Clients cannot self-promote. Verification is evaluated server-side. Pass task_structure_id (from cogniti