The unified observability layer for the AI Control Plane, delivering full-fidelity tracing for AI agent reasoning, tool calls, and state transitions.
Altar provides a robust, type-safe foundation for building AI agent tools in Elixir. It offers a clean contract to define and execute tools locally, with a clear promotion path to future distributed systems.
Protocol-based AI adapter foundation for Elixir. Provides unified abstractions for gemini_ex, claude_agent_sdk, and codex_sdk with automatic fallback support, runtime capability detection, and built-in telemetry.
Labeling queue library for managing human labeling workflows. Domain-agnostic HITL (human-in-the-loop) data annotation with inter-rater reliability metrics (Cohen's kappa, Fleiss' kappa, Krippendorff's alpha) and export to standard formats.
A metaprogramming framework for building REST APIs from OTP operations with automatic endpoint generation, parameter validation, and OpenAPI documentation.
The definitive CI/CD platform for AI Quality.
The command and control layer for the AI-powered enterprise.
An Elixir SDK for Claude Code - Build AI-powered CLI tools with Claude
An Elixir SDK for Claude Code - Build AI-powered CLI tools with Claude
Idiomatic Elixir SDK for OpenAI's Codex agent. Provides a complete, production-ready interface with streaming support, comprehensive event handling, and robust testing utilities.
Adversarial testing and robustness framework for AI models with 25 attacks (character/word/semantic perturbations, prompt injection, jailbreak, extraction, inversion), defenses (detection/filtering/sanitization), certified robustness metrics, and attack composition.
Comprehensive benchmarking framework for AI research. Measures latency, throughput, cost, and reliability with percentile analysis and Nx numerical computations.
Dataset management and caching for AI research benchmarks
Multi-model ensemble prediction with voting strategies for AI reliability. Leverages BEAM parallelism for massively concurrent LLM queries.
CrucibleFramework: A scientific platform for LLM reliability research on the BEAM. Provides core library functionality with comprehensive documentation and guides.
Experimental research framework for running AI benchmarks at scale. Provides orchestration, streaming processing with Flow/GenStage, and statistical analysis.
Request hedging for tail latency reduction in distributed systems. Implements Google's 'Tail at Scale' with adaptive strategies. Reduces P99 latency by 75-96%.
Intermediate Representation for the Crucible ML reliability ecosystem
Advanced telemetry collection and analysis for AI research
Structured causal reasoning chain logging for LLMs. Captures decision-making processes with cryptographic verification for transparency and debugging.
Explainable AI (XAI) tools for the Crucible framework. Includes LIME implementations, SHAP-like explanations, feature attribution, and model interpretability for local and global explanations.
Dataset management library for ML experiments with support for GSM8K, HumanEval, MMLU loaders and evaluation metrics (BLEU, ROUGE, F1).
DSPex: Native Elixir implementation of DSPy with Python integration via Snakepit. Enables gradual migration from Python DSPy to native Elixir implementations while supporting mixed execution pipelines.
A 100% faithful port of the DuckDB Python client to Elixir, using the DuckDB CLI for full API compatibility with the official Python client.
A Phoenix LiveView performance monitoring dashboard for tracking slow endpoints and database queries during development.
ElixirScope is a next-generation debugging and observability platform for Elixir applications, designed to provide an Execution Cinema experience through deep, compile-time AST instrumentation guided by AI-powered analysis.
Local-first observability for Elixir with New Relic API parity. A complete tracing and observability solution that works entirely offline while maintaining compatibility with New Relic's API surface.
Vector embeddings service for the NSAI ecosystem
Model evaluation harness for standardized benchmarking with semantic similarity, exact match, and custom metrics.
Production-ready data validation and quality library for Elixir ML pipelines. Provides 22 built-in expectations, drift detection, advanced profiling with outliers and correlations, statistical analysis, and comprehensive quality metrics for machine learning workflows.
Fairness and bias detection library for Elixir AI/ML systems. Provides comprehensive fairness metrics, bias detection algorithms, and mitigation techniques.
Generic Topological Data Analysis for Elixir
Advanced schema definition and validation library for Elixir
Asset-first data orchestration framework for Elixir/BEAM.
FlowStone integration for altar_ai - AI-powered data pipeline assets. Provides FlowStone.AI.Resource for unified AI access and FlowStone.AI.Assets DSL helpers (classify_each, enrich_each, embed_each) with telemetry bridging.
Sample factory library for generating, transforming, and computing measurements on arbitrary samples. Domain-agnostic data pipeline orchestration for ML dataset preparation.
A comprehensive Elixir infrastructure and observability library providing essential services for building robust, scalable applications.
Comprehensive Elixir client for Google's Gemini AI API with dual authentication, embeddings with MRL, streaming, type safety, and built-in telemetry for production applications.
Elixir implementation of the GEPA (Genetic-Pareto) optimizer that combines LLM-powered reflection with Pareto search to evolve text-based system components.
Phoenix LiveView interface for sample generation and human labeling workflows. Thin wrapper around Forge (sample factory) and Anvil (labeling queue) with real-time progress updates, keyboard shortcuts, and inter-rater reliability dashboards.
A blazingly fast Elixir library for repairing malformed JSON using binary pattern matching. Handles LLM outputs, legacy data, and broken JSON with intelligent context-aware fixes.
Elixir client library for the Jules API. Jules is an AI-powered coding assistant that can automate software development tasks across multiple repositories.
Shared IR structs for Forge, Anvil, Ingot, and external clients; typed datasets, samples, assignments, labels, artifacts, and evaluation runs for labeling workflows.
AI Firewall and guardrails for LLM-based Elixir applications. Provides prompt injection detection, data leakage prevention, jailbreak detection, and comprehensive security guardrails.
A multi-agent framework for the BEAM (Erlang VM) that provides agent lifecycle management, message passing, discovery, and extensibility for building distributed agent-based systems.
Metrics aggregation service for experiment results and system health monitoring.
Unified API Gateway for North Shore AI services - handles routing, authentication, rate limiting, and circuit breaking
North Shore AI Registry: Distributed model registry with PubSub coordination, health monitoring, and multi-backend storage for ML reliability research.
Composable regularization penalties and loss functions for the Nx ecosystem
A typing system for Elixir/OTP.
Interactive CLI/REPL for the NSAI ecosystem: unified interface for Crucible experiments, CNS dialectical synthesis, and ML reliability research.
AI pipeline orchestration library for Elixir. Chain Claude and Gemini APIs with robust execution, fault tolerance, and self-improving Genesis pipelines.
Cross-platform browser automation for Elixir with advanced WSL-to-Windows integration. Features headed browser support, Chrome profile integration, and WebSocket-based remote browser control for seamless automation across platforms.
Unified schema definition, validation, and JSON generation for Elixir.
Sinter is a focused, high-performance schema validation library designed specifically for dynamic frameworks like DSPy. It distills complex validation APIs into a single, powerful, and unified engine.
Aggregates and packages Claude skills from multiple Elixir projects into a single, validated bundle ready for distribution.
Configuration-driven Python library integration for Elixir. Automatically generate type-safe Elixir modules from declarative configs, enabling seamless integration with any Python library. Built on Snakepit for high-performance Python orchestration.
High-performance pooler and session manager for external language integrations. Supports Python, Node.js, Ruby, and more with gRPC streaming, session management, and production-ready process cleanup.
Battle-hardened OTP testing toolkit with chaos engineering, performance testing, and zero-sleep synchronization patterns for building robust Elixir applications.
Declarative, headless multi-agent runtime for code review orchestration with signals, workflows, and Postgres persistence.
Synapse integration for altar_ai - SDK-backed LLM providers for multi-agent workflows. Provides unified adapter layer for Gemini, Claude, and Codex with automatic fallback, workflow actions, signal handlers, and telemetry bridging.
Elixir SDK for Tinker: LoRA training, sampling, and future-based workflows with telemetry and HTTP/2.
A modern Elixir client for Weaviate vector database with support for collections, objects, batch operations, GraphQL queries, and vector search. Includes health checks and friendly error messages for missing configuration.