nshkr-crucible

AI Firewall and guardrails for LLM-based Elixir applications

Explainable AI (XAI) tools for the Crucible framework

Deterministic tensor patch plans, patch application, and tensor path traversal for neural network model surgery.

Experimental research framework for running AI benchmarks at scale

Fairness and bias detection library for Elixir AI/ML systems

Interactive Phoenix LiveView demonstrations of the Crucible Framework - showcasing ensemble voting, request hedging, statistical analysis, and more with mock LLMs

Statistical testing and analysis framework for AI research

Canonical Elixir signal ontology for transformer forward-pass artifacts, tensor summaries, capabilities, and internal-control surfaces.

Request hedging for tail latency reduction in distributed systems

Phoenix LiveView dashboard for the Crucible ML reliability stack

Intermediate Representation for the Crucible ML reliability ecosystem

Bumblebee, Axon, and Nx adapter layer for compiling Crucible tap plans into model runs, hooks, traces, and decode steering.

Data validation and quality library for ML pipelines in Elixir

Metrics aggregation and alerting for ML experiments—multi-backend export (Prometheus, InfluxDB, Datadog, OpenTelemetry), advanced aggregations (percentiles, histograms, moving averages), threshold-based alerting with anomaly detection (z-score, IQR), and time-series storage. Research-grade observability for the NSAI ecosystem.

Model evaluation harness for standardized benchmarking—comprehensive metrics (F1, BLEU, ROUGE, METEOR, BERTScore, pass@k), statistical analysis (confidence intervals, effect size, bootstrap CI, ANOVA), multi-model comparison, and report generation. Research-grade evaluation for LLM and ML experiments.

Bounded forward-pass trace schema and persistence helpers for Crucible signal captures, layer trajectories, and decode telemetry.

ML model deployment for the Crucible ecosystem. vLLM and Ollama integration, canary deployments, A/B testing, traffic routing, health checks, rollback strategies, and inference serving for Elixir-based ML workflows.

SafeTensors parsing, validation, bounded slicing, checksums, deterministic writing, and row-chunk helpers for Elixir and Nx.

CrucibleFramework: A scientific platform for LLM reliability research on the BEAM