crucible_ir

CrucibleFramework: A thin orchestration layer for experiment pipelines. Provides pipeline execution, stage behaviour, and optional persistence.

Published 5 months ago

AI Firewall and guardrails for LLM-based Elixir applications. Provides prompt injection detection, data leakage prevention, jailbreak detection, and comprehensive security guardrails.

Published 5 months ago

Dataset management and caching for AI research benchmarks

Published 5 months ago

Comprehensive benchmarking framework for AI research. Measures latency, throughput, cost, and reliability with percentile analysis and Nx numerical computations.

Published 5 months ago

Fairness and bias detection library for Elixir AI/ML systems. Provides comprehensive fairness metrics, bias detection algorithms, and mitigation techniques.

Published 5 months ago

Multi-model ensemble prediction with voting strategies for AI reliability. Leverages BEAM parallelism for massively concurrent LLM queries.

Published 5 months ago

Model versioning, artifact storage, and lineage tracking for ML pipelines

Published 3 months ago

Request hedging for tail latency reduction in distributed systems. Implements Google's 'Tail at Scale' with adaptive strategies. Reduces P99 latency by 75-96%.

Published 5 months ago

Explainable AI (XAI) tools for the Crucible framework. Includes LIME implementations, SHAP-like explanations, feature attribution, and model interpretability for local and global explanations.

Published 5 months ago

Adversarial testing and robustness framework for AI models with 25 attacks (character/word/semantic perturbations, prompt injection, jailbreak, extraction, inversion), defenses (detection/filtering...

Published 5 months ago

Structured causal reasoning chain logging for LLMs. Captures decision-making processes with cryptographic verification for transparency and debugging.

Published 5 months ago

Advanced telemetry collection and analysis for AI research

Published 5 months ago

Model deployment orchestration with health checking and rollback

Published 3 months ago

Unified ML training infrastructure for Elixir/BEAM

Published 3 months ago

Feedback collection, drift detection, and active learning for ML pipelines

Published 3 months ago