AI & ML Infrastructure on Elixir/BEAM

Building core AI and ML infrastructure libraries primarily on the BEAM platform. Creator of Crucible Framework for LLM reliability research.

Neural Networks

LLM Reliability

Distributed Systems

Distributed Systems

Developer Tools

50+ Libraries

Research

Research-Grade

Ensemble Methods

Ensemble Methods

50+
Open Source Libraries
Python 3.13+
Free-Threading Support
Active Dev
Crucible & Snakepit

North Shore AI Ecosystem

A 7-tiered industrial ML infrastructure built on Elixir and the BEAM platform

RAG Stack

Portfolio Ecosystem

Hexagonal architecture for Retrieval-Augmented Generation with 16 port specifications.

  • portfolio_core - 16 Ports, ETS Registry
  • portfolio_index - Pgvector, Neo4j, Broadway
  • portfolio_manager - CLI, Multi-Provider
  • portfolio_coder - Code Intelligence
Orchestration

Data & Agent Coordination

Complementary frameworks for data pipelines and multi-agent systems.

  • flowstone - Asset-first data orchestration
  • synapse - Multi-agent signal bus
  • Lineage tracking & partition-aware execution
  • Durable workflows with Postgres persistence
Reasoning

CNS Dialectical Engine

Thesis-Antithesis-Synthesis reasoning with critic-guided resolution.

  • Proposer - Thesis generation, SNO extraction
  • Antagonist - Contradiction detection, B1 gaps
  • Synthesizer - Evidence-based resolution
  • 5 Critics - Grounding, Logic, Novelty, Bias, Causal
Metaphors

Industrial Patterns

Organizing metaphors that encode architectural decisions into memorable concepts.

  • Kitchen - Training infrastructure (crucible_kitchen)
  • Cookbook - Training recipes (tinkex_cookbook)
  • Forge/Anvil/Ingot - Data labeling stack
  • Crucible - ML experimentation

Ingot Data Labeling

anvil
⭐ 1

Labeling queue library for managing human labeling workflows

View on GitHub →
forge
⭐ 1

Sample factory library for generating, transforming, and computing measurements on samples

View on GitHub →
ingot
⭐ 1

Phoenix LiveView interface for sample generation and human labeling workflows

View on GitHub →
labeling_ir
⭐ 1

Shared IR structs for the North Shore labeling stack (Forge/Anvil/Ingot) — typed datasets, samples, assignments, labels, artifacts, and evaluation runs for labeling workflows

View on GitHub →

AI Agent Orchestration

synapse
⭐ 34

Headless, declarative multi-agent orchestration framework with a domain-agnostic signal bus, workflow engine with Postgres persistence, and configurable agent runtime (ships code review domain).

View on GitHub →
ds_ex
⭐ 15

DSPEx - Declarative Self-improving Elixir | A BEAM-Native AI Program Optimization Framework

View on GitHub →
flowstone
⭐ 13

Asset-first data orchestration for Elixir/BEAM. Dagster-inspired with OTP fault tolerance, LiveView dashboard, lineage tracking, checkpoint gates, and distributed execution via Oban.

View on GitHub →
DSPex
⭐ 10

Declarative Self Improving Elixir - DSPy Orchestration in Elixir

View on GitHub →
pipeline_ex
⭐ 7

Claude Code + Gemini AI collaboration orchestration tools

View on GitHub →
ALTAR
⭐ 6

The Agent & Tool Arbitration Protocol

View on GitHub →
mabeam
⭐ 5

Multi-agent systems framework for the BEAM platform - build distributed autonomous agents with OTP supervision and fault tolerance

View on GitHub →
flowstone_ai
⭐ 1

FlowStone integration for altar_ai - AI-powered data pipeline assets with classify_each, enrich_each, embed_each helpers and unified telemetry

View on GitHub →
synapse_ai
⭐ 1

Synapse integration for altar_ai - SDK-backed LLM providers for multi-agent workflows with automatic fallback, signal handlers, and workflow actions

View on GitHub →

AI SDKs & API Clients

gemini_ex
⭐ 22

Elixir Interface / Adapter for Google Gemini LLM, for both AI Studio and Vertex AI

View on GitHub →
claude_agent_sdk
⭐ 16

An Elixir SDK for Claude Code - provides programmatic access to Claude Code CLI with streaming message processing

View on GitHub →
codex_sdk
⭐ 5

OpenAI Codex SDK written in Elixir

View on GitHub →
jules_ex
⭐ 2

Elixir client SDK for the Jules API - orchestrate AI coding sessions

View on GitHub →
altar_ai
⭐ 1

Protocol-based AI adapter foundation for Elixir - unified abstractions for gemini_ex, claude_agent_sdk, codex_sdk with automatic fallback, capability detection, and telemetry

View on GitHub →
ollixir
⭐ 1

Ollixir provides a first-class Elixir client with feature parity to the official ollama-python library. Ollixir runs large language models locally or on your infrastructure via Ollama.

View on GitHub →
crucible_prompts
⭐ 0

Prompt and parsing utilities for Crucible and NSAI. Provides templating, schema validation, structured output parsing, and tool-call helpers for consistent LLM IO.

View on GitHub →
mcp_client
⭐ 0

Full-featured Elixir client for the Model Context Protocol (MCP) with multi-transport support, resources, prompts, tools, and telemetry.

View on GitHub →
nsai_llm
⭐ 0

Shared LLM Actions for NSAI runtimes. Wraps PortfolioCore adapters with Jido.Action semantics and CrucibleIR.Backend input/output to centralize provider access.

View on GitHub →
vllm
⭐ 0

vLLM - High-throughput, memory-efficient LLM inference engine with PagedAttention, continuous batching, CUDA/HIP optimization, quantization (GPTQ/AWQ/INT4/INT8/FP8), tensor/pipeline parallelism, OpenAI-compatible API, multi-GPU/TPU/Neuron support, prefix caching, and multi-LoRA capabilities

View on GitHub →

AI Infrastructure

json_remedy
⭐ 23

A practical, multi-layered JSON repair library for Elixir that intelligently fixes malformed JSON strings commonly produced by LLMs, legacy systems, and data pipelines.

View on GitHub →
snakepit
⭐ 10

High-performance, generalized process pooler and session manager for external language integrations. Orchestrates and supervises languages like Python and Javascript from Elixir.

View on GitHub →
snakebridge
⭐ 3

Compile-time Elixir code generator for Python library bindings. Declare dependencies in mix.exs, generate type-safe modules with introspected typespecs and docs. Deterministic git-friendly output, strict CI mode, streaming, and custom helpers. Runtime via Snakepit.

View on GitHub →
rag_ex
⭐ 2

Elixir RAG library with multi-LLM routing (Gemini, Claude, OpenAI, Ollama), GraphRAG, knowledge graphs, modular retrievers/rerankers, composable pipelines, pgvector integration, advanced chunking, and tool-using agents. Fork of bitcrowd/rag.

View on GitHub →
tinkex
⭐ 2

Elixir SDK for the Tinker ML platform—LoRA training, sampling, and service orchestration built on OTP, Finch, and telemetry.

View on GitHub →
command
⭐ 1

Core Elixir library for AI agent orchestration - unified workbench for running, tracking, and orchestrating multi-provider LLM agents with sessions, workflows, RAG indexes, tool approvals, and cost tracking

View on GitHub →
gepa_ex
⭐ 1

Elixir implementation of GEPA: LLM-driven evolutionary optimization using Pareto-efficient search for text-based systems. Features OpenAI/Gemini integration, BEAM concurrency, OTP supervision, 218 tests with 75% coverage.

View on GitHub →
nsai_gateway
⭐ 1

Unified API gateway for the NSAI ecosystem—authentication (JWT, API keys, OAuth2/OIDC), distributed rate limiting with burst allowance, circuit breakers, request tracing, Prometheus metrics, and service proxying. Production-ready with comprehensive observability and multi-tenant support.

View on GitHub →
nsai_registry
⭐ 1

Service discovery and registry for the NSAI ecosystem—distributed registry with health checking, circuit breakers, multiple storage backends (ETS/PostgreSQL), PubSub event broadcasting, and comprehensive telemetry. Built on OTP with Horde-ready architecture for multi-node deployments.

View on GitHub →
pilot
⭐ 1

Interactive CLI and REPL for the NSAI ecosystem—unified interface to registry, gateway, jobs, experiments, datasets, embeddings, and metrics services; tab completion with bash/zsh scripts; configurable environments; JSON output mode for scripting; escript distribution. The cockpit for North Shore AI operations.

View on GitHub →
skill_ex
⭐ 1

Claude Skill Aggregator

View on GitHub →
tiktoken_ex
⭐ 1

Pure Elixir TikToken-style byte-level BPE tokenizer (Kimi K2 compatible).

View on GitHub →
tinkerer
⭐ 1

Chiral Narrative Synthesis workspace for Thinker/Tinker LoRA pipelines, semantic fact-checking, telemetry, and reviewer-ready CNS docs.

View on GitHub →
tinkex_cookbook
⭐ 1

Elixir port of tinker-cookbook: training and evaluation recipes for the Tinker ML platform.

View on GitHub →
work
⭐ 1

NSAI.Work - Unified job scheduler for North-Shore-AI platform

View on GitHub →
hf_hub_ex
⭐ 0

Elixir client for HuggingFace Hub—dataset/model metadata, file downloads, caching, and authentication. The BEAM-native foundation for HF ecosystem ports.

View on GitHub →
hf_peft_ex
⭐ 0

Elixir port of HuggingFace's PEFT (Parameter-Efficient Fine-Tuning) library. Implements LoRA, AdaLoRA, IA3, prefix tuning, prompt tuning, and 30+ state-of-the-art PEFT methods for efficient neural network adaptation. Built for the BEAM ecosystem with native Nx/Axon integration.

View on GitHub →
portfolio_core
⭐ 0

Hexagonal architecture core for Elixir RAG systems. Port specifications, manifest-based config, adapter registry, and DI framework. Enables swappable vector/graph/embedding/LLM backends via clean port/adapter abstractions. Hex.pm publishable.

View on GitHub →
portfolio_index
⭐ 0

Production adapters and pipelines for PortfolioCore. Vector stores (pgvector, Qdrant), graph stores (Neo4j), embedders (OpenAI), Broadway pipelines, advanced RAG (Self-RAG, CRAG, GraphRAG, Agentic), multi-graph federation, and observability.

View on GitHub →
portfolio_manager
⭐ 0

AI-native personal project intelligence system - manage, track, and search across all your repositories with semantic understanding

View on GitHub →

Schema & Validation

exdantic
⭐ 10

A powerful, flexible schema definition and validation library for Elixir, inspired by Python's Pydantic.

View on GitHub →
sinter
⭐ 10

Unified schema definition, validation, and JSON generation for Elixir

View on GitHub →
perimeter
⭐ 7

Advanced typing and type validation mechanism for Elixir - runtime type checking and contract enforcement for BEAM applications

View on GitHub →
batch_ir
⭐ 0

Batch IR for standardized data interchange across training and inference backends. Covers text/token/chat/instruct batch types with encoding, validation, and portable schemas.

View on GitHub →

Developer Tools

ex_dbg
⭐ 10

State-of-the-Art Introspection and Debugging System for Elixir/Phoenix Applications

View on GitHub →
ElixirScope
⭐ 5

AI-Powered Execution Cinema Debugger for Elixir/BEAM

View on GitHub →
elixir_scope
⭐ 5

Revolutionary AST-based debugging and code intelligence platform for Elixir applications

View on GitHub →
elixir_dashboard
⭐ 2

A Phoenix LiveView performance monitoring dashboard for tracking slow endpoints and database queries

View on GitHub →
elixir_tracer
⭐ 1

Local-first observability for Elixir with New Relic API parity

View on GitHub →
portfolio_coder
⭐ 0

Code Intelligence Platform: Repository analysis, semantic code search, dependency graphs, and AI-powered code understanding built on the Portfolio RAG ecosystem. Features multi-language parsing (Elixir, Python, JavaScript, TypeScript), AST-aware chunking, call graph analysis, and intelligent code agents for review, refactoring, and documentation.

View on GitHub →
pristine
⭐ 0

Manifest-driven hexagonal core for generating Elixir SDKs and services with pluggable ports/adapters for transport, schema, retries, telemetry, streaming, and multipart.

View on GitHub →

OTP & Distributed

superlearner
⭐ 8

OTP Supervisor Educational Platform

View on GitHub →
apex
⭐ 4

Core Apex framework for OTP supervision and monitoring

View on GitHub →
apex_ui
⭐ 4

Web UI for Apex OTP supervision and monitoring tools

View on GitHub →
arsenal
⭐ 4

Metaprogramming framework for automatic REST API generation from OTP operations

View on GitHub →
arsenal_plug
⭐ 3

Phoenix/Plug adapter for Apex Arsenal framework

View on GitHub →

Testing & QA

supertester
⭐ 7

A battle-hardened testing toolkit for building robust and resilient Elixir & OTP applications.

View on GitHub →
playwriter
⭐ 6

Elixir WSL-to-Windows browser integration

View on GitHub →
cluster_test
⭐ 4

Distributed Erlang/Elixir test cluster management via Mix tasks

View on GitHub →
sandbox
⭐ 4

Isolated OTP application management system for Elixir/Erlang

View on GitHub →

Observability

foundation
⭐ 11

Elixir infrastructure and Observability Library

View on GitHub →
AITrace
⭐ 1

The unified observability layer for the AI Control Plane

View on GitHub →
Citadel
⭐ 1

The command and control layer for the AI-powered enterprise

View on GitHub →
lineage_ir
⭐ 0

Lineage IR for cross-system traces, spans, artifacts, and provenance edges. Provides a shared event envelope and sink interface for consolidation across runtimes.

View on GitHub →
telemetry_reporter
⭐ 0

Pachka-powered telemetry reporter for Elixir that batches client-side events, supports pluggable transports and :telemetry forwarding, and drains reliably on shutdown.

View on GitHub →

Data & Databases

duckdb_ex
⭐ 1

DuckDB driver client in Elixir

View on GitHub →
embed_ex
⭐ 1

Vector embeddings service for Elixir—multi-provider support (OpenAI, Cohere, Voyage AI), intelligent caching with Cachex, batch processing with rate limiting, Nx-powered similarity computations, k-means/DBSCAN clustering, semantic deduplication, and ETS-based vector storage. Built for CNS and ML pipelines.

View on GitHub →
weaviate_ex
⭐ 1

Modern Elixir client for Weaviate vector database with health checks and friendly error messages

View on GitHub →
ex_topology
⭐ 0

Pure Elixir library for graph topology, TDA, and computational topology

View on GitHub →
nx_penalties
⭐ 0

Composable regularization penalties for Elixir Nx. L1/L2/Elastic Net, KL divergence, entropy, consistency, gradient penalty, orthogonality. Pure Nx.Defn for JIT across EXLA/Torchx. Pipeline composition and Axon.Loop integration.

View on GitHub →

Security

GUARDRAIL
⭐ 16

GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits

View on GitHub →
ASKA
⭐ 7

Secure Computing in the AI age

View on GitHub →
pqc-hqc
⭐ 5

Post-quantum cryptographic implementation of HQC (Hamming Quasi-Cyclic) - a NIST PQC candidate for quantum-resistant key encapsulation using code-based cryptography

View on GitHub →
Shield
⭐ 0

SHIELD: Secure Hierarchical Inter-agent Layer for Distributed Environments

View on GitHub →

Research

ChronoLedger
⭐ 2

Hardware-Secured Temporal Blockchain

View on GitHub →
cns
⭐ 1

Chiral Narrative Synthesis - Dialectical reasoning framework for automated knowledge discovery

View on GitHub →
EADS
⭐ 0

Evolutionary Autonomous Development System

View on GitHub →
cns_ui
⭐ 0

Phoenix LiveView interface for CNS dialectical reasoning experiments

View on GitHub →

Utilities

youtube_audio_dl
⭐ 2

Download high-quality audio from YouTube as MP3 files using Elixir. Features 104 music genres, duration filtering, per-genre caching, C++ DSP filters, and ML-based transient detection.

View on GitHub →
tools
⭐ 1

Utility library and helper functions for Elixir development - common patterns, debugging aids, and productivity tools

View on GitHub →
chz_ex
⭐ 0

Elixir port of OpenAI's chz library - a powerful configuration management system for building composable, type-safe command-line interfaces with hierarchical configuration, environment variable support, and flexible argument parsing

View on GitHub →
multipart_ex
⭐ 0

Client-agnostic multipart/form-data builder for Elixir with explicit file inputs, stream-first encoding, configurable form serialization, and adapters for common HTTP clients.

View on GitHub →

Crucible Framework

A platform for conducting reproducible experiments on large language model reliability, built on Elixir/OTP.

Elixir OTP BEAM VM Statistical Testing Ensemble Methods
LlmGuard
⭐ 4

AI Firewall and guardrails for LLM-based Elixir applications

View on GitHub →
crucible_examples
⭐ 1

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

View on GitHub →
ExDataCheck
⭐ 0

Data validation and quality library for ML pipelines in Elixir

View on GitHub →
ExFairness
⭐ 0

Fairness and bias detection library for Elixir AI/ML systems

View on GitHub →
cns_crucible
⭐ 0

View on GitHub →
crucible_adversary
⭐ 0

Adversarial testing and robustness evaluation for the Crucible framework

View on GitHub →
crucible_bench
⭐ 0

Statistical testing and analysis framework for AI research

View on GitHub →
crucible_datasets
⭐ 0

Dataset management and caching for AI research benchmarks

View on GitHub →
crucible_deployment
⭐ 0

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.

View on GitHub →
crucible_ensemble
⭐ 0

Multi-model ensemble voting strategies for LLM reliability

View on GitHub →
crucible_feedback
⭐ 0

ML feedback loop management for the Crucible ecosystem. Quality monitoring, data drift detection, model performance tracking, data curation, active learning, human-in-the-loop workflows, and continuous improvement for Elixir-based ML.

View on GitHub →
crucible_framework
⭐ 0

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

View on GitHub →
crucible_harness
⭐ 0

Experimental research framework for running AI benchmarks at scale

View on GitHub →
crucible_hedging
⭐ 0

Request hedging for tail latency reduction in distributed systems

View on GitHub →
crucible_ir
⭐ 0

Intermediate Representation for the Crucible ML reliability ecosystem

View on GitHub →
crucible_kitchen
⭐ 0

Industrial ML training orchestration - backend-agnostic workflow engine for supervised, reinforcement, and preference learning. Provides composable workflows, declarative stage DSL, comprehensive telemetry, and port/adapter patterns for any ML backend. The missing orchestration layer that makes ML cookbooks trivially thin.

View on GitHub →
crucible_model_registry
⭐ 0

ML model registry for the Crucible ecosystem. Artifact storage, model versioning, lineage tracking, metadata management, model comparison, reproducibility, and integration with training pipelines for Elixir-based ML workflows.

View on GitHub →
crucible_telemetry
⭐ 0

Advanced telemetry collection and analysis for AI research

View on GitHub →
crucible_trace
⭐ 0

Structured causal reasoning chain logging for LLM transparency

View on GitHub →
crucible_train
⭐ 0

ML training orchestration for the Crucible ecosystem. Distributed training, hyperparameter optimization, checkpointing, model versioning, metrics collection, early stopping, LR scheduling, gradient accumulation, and mixed precision training with Nx/Scholar integration.

View on GitHub →
crucible_ui
⭐ 0

Phoenix LiveView dashboard for the Crucible ML reliability stack

View on GitHub →
crucible_xai
⭐ 0

Explainable AI (XAI) tools for the Crucible framework

View on GitHub →
datasets_ex
⭐ 0

Dataset management library for ML experiments—loaders for SciFact, FEVER, GSM8K, HumanEval, MMLU, TruthfulQA, HellaSwag; git-like versioning with lineage tracking; transformation pipelines; quality validation with schema checks and duplicate detection; GenStage streaming for large datasets. Built for reproducible AI research.

View on GitHub →
eval_ex
⭐ 0

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.

View on GitHub →
hf_datasets_ex
⭐ 0

HuggingFace Datasets for Elixir - A native Elixir port of the popular HuggingFace datasets library. Stream, load, and process ML datasets from the HuggingFace Hub with full BEAM/OTP integration. Supports Parquet streaming, dataset splitting, shuffling, and seamless integration with Nx tensors for machine learning workflows.

View on GitHub →
metrics_ex
⭐ 0

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.

View on GitHub →
training_ir
⭐ 0

Training IR for reproducible ML jobs across Crucible and Kitchen. Defines model specs, adapters, learning config, checkpointing, validation, and resource envelopes to standardize training pipelines.

View on GitHub →

Other Projects

nshkrdotcom
⭐ 0

Personal GitHub profile README with Elixir/AI projects and LLM reliability research

View on GitHub →

Tech Stack

Elixir Erlang Python JavaScript/TypeScript Rust Phoenix OTP FastAPI React BEAM VM AWS GCP Cloudflare Workers

Specialties

  • Distributed systems & fault tolerance
  • AI/LLM infrastructure & reliability
  • Functional programming & metaprogramming
  • Statistical analysis & experimental design
  • Developer tools & productivity