Examples Portfolio
34 Production-Quality Examples in Multiple Languages Real-World Solutions
Every example runs out of the box in Rust, Go, or Python.
20 patterns also ship as CLI/Bash implementations for shell automation and CI.
From basic chat to multi-engine orchestration — pick a pattern, choose your language, and launch.
LLM Patterns
Core patterns for working with cloud and local language models — chat, streaming, structured output, retries, cost routing, and more.
Basic Chat
Send your first LLM chat message in minutes, then swap providers without touching your application code.
Basic chat completion with a simple prompt
Real-world applications
- Customer support chatbot, FAQ assistant
Streaming
Stream LLM responses token by token with a unified async interface that works across Claude, OpenAI, and Ollama without changing your code.
Streaming chat completion with real-time output
Real-world applications
- Real-time chat interface, live transcription display
Multi Provider
Run the same prompt across Claude, OpenAI, and Ollama simultaneously using one unified interface that normalizes responses and token usage.
Using multiple providers in one application
Real-world applications
- Multi-vendor AI gateway, provider comparison tool
Convenience Api
Skip the boilerplate: call any LLM with a single line, letting nxusKit detect your provider and credentials automatically.
LiteLLM-style convenience API usage
Real-world applications
- Rapid prototyping, scripting with LLM capabilities
Blocking Api
Call LLMs synchronously from any Rust code — no async runtime required, no await syntax, no tokio dependency to manage.
Synchronous blocking API for simpler use cases
Real-world applications
- CLI tools, batch processing scripts
Capability Detection
Stop hardcoding model names — query provider capabilities at runtime and let task requirements drive model selection across any LLM backend.
Detecting provider capabilities at runtime
Real-world applications
- Adaptive AI middleware, feature-gated UX
Cost Routing
Route every LLM request to the right model for the job, so you stop paying premium prices for economy-grade tasks.
Cost-aware provider routing and selection
Real-world applications
- Cost-optimized inference, budget-aware model selection, prompt complexity tiering
Polymorphic
Swap LLM providers at runtime without touching your application logic — nxusKit's polymorphic patterns keep your code provider-agnostic from day one.
Polymorphic provider patterns with trait objects
Real-world applications
- Plugin architecture, provider-agnostic application layer
Retry Fallback
Chain multiple LLM providers together so a failed request automatically reroutes to the next available provider without changing your application code.
Retry and fallback strategies across providers
Real-world applications
- High-availability AI service, resilient inference pipeline
Structured Output
Stop parsing free-form LLM text — get typed, validated JSON structs back every time, across every provider.
JSON mode and structured output generation
Real-world applications
- Data extraction, form auto-fill, API response generation
Timeout Config
Take control of LLM request timing with per-phase timeout configuration that catches network failures fast without killing long-running streams.
Timeout configuration and connection management
Real-world applications
- Latency-sensitive services, SLA-bound AI endpoints
Token Budget
Stop paying for tokens you don't need — enforce real-time streaming budgets and cancel LLM requests the moment your limit is reached.
Token budget management and cost estimation
Real-world applications
- Usage metering, per-user quota enforcement
Vision
Send images alongside text to any LLM provider using one consistent API that handles encoding, formatting, and provider differences for you.
Vision and multimodal capabilities with images
Real-world applications
- Image captioning, visual QA, document understanding
Auth Helper
Wire up OAuth flows and API key credentials across every provider your app supports, with a single unified auth interface.
Scenarios
-
statusList provider authentication status and stored credentials -
setStore an API key for a specific provider -
removeRemove a stored API key for a provider -
dashboardOpen provider credential dashboard in browser
OAuth login flow and credential management helper
Real-world applications
- Developer tooling, credential management, multi-provider auth setup
Ollama
Run open-source LLMs on your own hardware using the same nxusKit interface you already use for Claude and OpenAI.
Using Ollama for local inference
Real-world applications
- On-premise AI deployment, air-gapped inference
Lmstudio
Run LLM inference on your own machine — connect nxusKit to LM Studio and prototype without cloud dependencies or API keys.
Using LM Studio for local inference
Real-world applications
- Developer local testing, offline prototyping
Alert Triage
Turn alert noise into prioritized action by letting an LLM classify severity, surface root causes, and recommend remediation steps automatically.
Alert triage with LLM-powered analysis
Real-world applications
- SOC alert triage, IT incident management
Cli Assistant
Turn plain English into shell commands instantly — build a streaming CLI assistant that speaks your language and runs in your terminal.
Interactive CLI assistant with LLM backend
Real-world applications
- Developer productivity tool, command-line copilot
Clips Llm Hybrid
Combine deterministic CLIPS rules with LLM reasoning to build AI pipelines that are both fluent and auditable.
Hybrid CLIPS rules + LLM reasoning
Real-world applications
- Explainable AI decisions, regulated industry automation
Common Sense Guardrails
Catch plausible but impossible LLM recommendations by turning answers into facts, firing rules, and repairing failures with auditable prompts.
Scenarios
-
car-washCatch the classic car-wash walk-vs-drive failure with CLIPS rules and optional Solver/Z3 feasibility -
coupon-stackReject promotion stacking that violates eligibility and margin policy, with optional ZEN validation and BN risk scoring -
pallet-doorBlock unsafe warehouse advice that ignores dimensional clearance, with optional Solver/Z3 feasibility -
cold-chainPrevent cheaper logistics recommendations that violate handling requirements, with optional ZEN validation and BN review-risk scoring
Progressive LLM guardrails with CE CLIPS/BN and optional Pro Solver/ZEN repair feedback
Real-world applications
- LLM answer validation Catch plausible recommendations that fail physical, operational, or policy preconditions before they reach users
- Policy enforcement Turn free-form answers into facts, apply deterministic rules, and produce auditable repair context
- Operational decision support Preserve fast LLM drafting while requiring concrete feasibility evidence for workflow-critical recommendations
Model Research Harness
Research model fitness with provider-neutral runs, Promptfoo import, deterministic policy checks, Bayesian confidence, and dry-run lifecycle recommendations.
Scenarios
-
basic-ticket-routingRun a credentials-free support ticket classification research smoke -
promptfoo-importImport a Promptfoo config and run the converted nxusKit harness matrix -
software-devEvaluate code analysis, bug finding, patching, generation, refactoring, and review outputs
Python-first harness for provider-neutral model research, Promptfoo import, CLIPS policy, Bayesian scoring, and dry-run lifecycle recommendations
Real-world applications
- Model evaluation Score model candidates against task-specific outputs and report confidence instead of relying on ad hoc impressions
- Provider comparison Compare local and cloud providers through one provider-neutral workflow while keeping capability claims honest
- Lifecycle policy Generate dry-run pull, pin, keep, or retest recommendations bounded by deterministic policy
- Software development workflow research Exercise code analysis, bug finding, bugfixing, generation, refactoring, and review scenarios with public-safe fixtures
Llm Solver Hybrid
Bridge natural language and constraint solvers — let an LLM parse human intent, let Z3 find the optimal answer.
Scenarios
-
seatingWedding dinner seating — 12 guests across 3 tables with constraints -
dungeonDungeon layout — 5 rooms with boss and treasure placement rules -
road-tripRoad trip planning — 14 days across 5 national parks with preferences
Hybrid LLM + Z3 solver problem solving
Real-world applications
- Natural language optimization, conversational planning
Puzzler
Compare CLIPS rule-based constraint solving against LLM reasoning side by side, then combine both in a hybrid approach for real puzzle problems.
Scenarios
-
sudokuSolve Sudoku puzzles using CLIPS constraint propagation -
set-gameFind valid SET card combinations using CLIPS pattern matching -
compareSide-by-side comparison of CLIPS, LLM, and hybrid solvers
Multi-approach puzzle solver comparing CLIPS, LLM, and hybrid strategies
Real-world applications
- AI strategy comparison, constraint vs neural solving benchmarks, educational puzzle platforms
Racer
Race CLIPS rule engines against LLMs on logic puzzles and let the data choose your AI strategy.
Scenarios
-
raceHead-to-head CLIPS vs LLM race on a single problem -
benchmarkStatistical benchmarking with multiple runs and timing -
listList all available problems with difficulty ratings -
describeShow detailed description of a specific problem
CLIPS vs LLM head-to-head benchmarking tool
Real-world applications
- AI approach comparison, rule engine vs LLM benchmarking, hybrid strategy selection
Riffer
Analyze, score, and transform MIDI and MusicXML sequences using CLIPS rule-based music theory and LLM-powered narrative and transformation.
Scenarios
-
analyzeAnalyze a music sequence for key, intervals, and rhythm patterns -
scoreScore a sequence on six musical dimensions -
transformTransform a sequence — transpose, invert, or retrograde -
convertConvert between MIDI and MusicXML formats
Music sequence analysis and transformation tool (still learning to shred)
Real-world applications
- Music theory analysis, algorithmic composition assistance, MIDI/MusicXML processing
Ruler
Turn plain English into validated CLIPS rules — describe your business logic, get production-ready expert system code with automatic error correction.
Scenarios
-
generateGenerate CLIPS rules from natural language descriptions -
validateValidate CLIPS rule syntax and semantic correctness -
saveSave generated rules to a file for later use -
loadLoad previously saved rules from a file -
examplesRun progressive complexity examples demonstrating rule generation
LLM-powered CLIPS rule generator with automatic validation
Real-world applications
- Low-code rule authoring, natural language business logic, automated CLIPS code generation
Arbiter
Stop accepting unreliable LLM output — validate every response against CLIPS rules and retry automatically until your standards are met.
Scenarios
-
classificationCategorize input text into specified categories -
extractionExtract structured information from unstructured text -
reasoningPerform logical inference and multi-step reasoning
CLIPS-validated LLM retry app with rule-based answer verification
Real-world applications
- Reliable AI answers with deterministic validation, LLM output verification, hybrid rule+LLM pipelines
Rule Engines & Decision Tables
Deterministic reasoning with CLIPS rules and ZEN decision tables — alone or combined with LLMs for hybrid AI pipelines.
Clips Basics
Bring deterministic rule-based logic to your applications by driving the CLIPS inference engine directly through the nxusKit SDK.
CLIPS rule engine basics via nxusKit SDK
Real-world applications
- Business rules engine, compliance checking
Bn Solver Clips Pipeline
Chain probabilistic prediction, constraint optimization, and rule-based safety enforcement into a single production-ready pipeline using one unified SDK.
Scenarios
-
festivalMusic festival staging — crowd predictions drive band scheduling and safety -
rescueSearch and rescue — survivor probability drives team assignment and safety checks -
bakeryBakery scheduling — demand forecasts drive oven allocation and allergen separation
Three-stage BN prediction → Solver optimization → CLIPS safety pipeline
Real-world applications
- Event planning Predict attendance, optimize resource allocation, enforce safety codes
- Emergency response Estimate survival windows, deploy rescue assets, enforce operational protocols
- Manufacturing Forecast demand, schedule production, enforce quality and safety standards
- Logistics Predict delivery volumes, optimize fleet routing, enforce regulatory compliance
- Healthcare Predict patient load, optimize staff scheduling, enforce clinical safety protocols
Zen Decisions
Evaluate business decision tables in Go, Rust, and Python using the ZEN engine — from pricing rules to eligibility checks, with first-hit and collect hit policies.
Scenarios
-
maze-ratFirst Hit Policy — route a maze runner through personality-driven decisions -
potionCollect Hit Policy — match ingredient lists against brewing recipes -
food-truckExpression Nodes — compute dynamic pricing with conditional logic
ZEN decision table evaluation via nxusKit SDK
Real-world applications
- Pricing rules, eligibility determination, policy evaluation
Constraint Solvers
Z3-based constraint solving for optimization, scheduling, and what-if analysis through the nxusKit solver API.
Solver
Define variables, add constraints, and solve complex planning problems with Z3 — without leaving your nxusKit workflow.
Scenarios
-
theme-parkBudget and space planning for a theme park with rides, food courts, and entertainment zones -
space-colonyResource allocation for a space colony dealing with solar storm what-if scenarios -
fantasy-draftFantasy sports draft optimization under salary cap with injury what-if analysis
Z3 constraint solver integration via nxusKit SDK
Real-world applications
- Theme Park Planning Facility layout, capital budgeting, resource allocation
- Space Colony Planning Infrastructure sizing, capacity planning, disaster recovery modeling
- Fantasy Sports Draft Portfolio optimization, team composition, auction bidding strategies
Solver What If
Explore alternative outcomes without rebuilding your model — push constraints, solve, compare, and pop back to baseline in one clean pattern.
Scenarios
-
weddingWedding budget planning with $25k constraint and vendor what-if scenarios -
marsMars colony resource allocation with dust storm what-if disruptions -
recipeRecipe scaling with vegan substitution — may be UNSAT
What-if scenario analysis with solver scoping
Real-world applications
- Wedding Budget Planning Event planning, capital budgeting, portfolio allocation
- Mars Colony Planning Infrastructure sizing, supply chain planning, disaster preparedness
- Recipe Scaling Manufacturing scaling, formulation optimization, process engineering
Probabilistic Reasoning
Bayesian networks for inference, structure learning, and probabilistic modeling integrated into application workflows.
Bayesian Inference
Run exact and approximate Bayesian inference on real-world diagnostic models using four algorithms and three themed scenarios — all from a single SDK call.
Scenarios
-
haunted-houseInvestigate a haunted house — is it a ghost or a raccoon? -
coffee-shopDiagnose bad espresso from grind size, temperature, and bean age -
plant-doctorDiagnose a sick plant from overwatering, nutrient, and disease evidence
Bayesian network inference via nxusKit SDK
Real-world applications
- Haunted House Fault diagnosis, anomaly detection, sensor fusion from multiple noisy sensors pointing to hidden causes
- Coffee Shop Manufacturing quality control, process parameter tuning, root cause analysis in production
- Plant Doctor Medical diagnosis, agricultural advisory systems, multi-symptom differential diagnosis
Bn Structure Learning
Discover causal structure hidden in your data — learn Bayesian network topology and parameters directly from CSV observations using Hill-Climb and K2 search algorithms.
Scenarios
-
golfGolf course conditions — weather, soil, and maintenance factor learning -
bmxBMX performance — skill level, technique, and jump factor learning -
sourdoughSourdough baking — feeding schedule, flour type, and temperature factor learning
Bayesian network structure learning from data
Real-world applications
- Epidemiology Discover disease risk factor relationships from patient records
- Manufacturing Identify root causes of defects from production data
- Finance Map causal relationships between economic indicators
- Genomics Learn gene regulatory networks from expression data
- Quality control Find which process parameters affect product quality