Packages

vLLM for Elixir via SnakeBridge - Easy, fast, and cheap LLM serving for everyone. High-throughput LLM inference with PagedAttention, continuous batching, and OpenAI-compatible API.

Application layer for Portfolio ecosystem providing RAG workflows, graph analysis, domain registries, and CLI tools built on portfolio_core and portfolio_index.

The command and control layer for the AI-powered enterprise.

Generic Elixir toolkit for deploying, observing, and readiness-verifying Coolify apps

Composable regularization penalties and loss functions for the Nx ecosystem

Model deployment orchestration with health checking and rollback

Unified ML training infrastructure for Elixir/BEAM

Reusable semantic inference contracts, adapters, tracing, and conformance tests for Elixir AI systems.

Generic Topological Data Analysis for Elixir

Client-agnostic multipart/form-data builder with explicit file handling and streaming encoding. Safe, predictable file inputs and configurable serialization strategies for complex forms. Adapters for common HTTP clients provided without coupling the core to any specific client.

A typing system for Elixir/OTP.

Shared runtime substrate for first-party OpenAPI-based Elixir SDKs.

Pure-Elixir TikToken-style byte-level BPE tokenizer, with helpers for Kimi K2 encodings.

Elixir SDK for the Notion API, built on Pristine's hexagonal architecture. Ported from the official notion-sdk-js.

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

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.

HuggingFace Datasets for Elixir - Load, stream, and process ML datasets from the HuggingFace Hub with native BEAM/OTP integration.

Native Elixir SDK for the GitHub REST API with generated endpoint modules, OTP-friendly runtime defaults, OAuth helpers, GitHub App helpers, pagination utilities, and publication-ready docs.

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

Declarative, headless multi-agent runtime for code review orchestration with signals, workflows, and Postgres persistence.