LLMz - An LLM-native Typescript VM built on top of Zui

Contains generic data manipulation functions that can be used in various components.

Type safe replacement for node's EventEmitter

Infer strong typings for commander options and action handlers

LLM inference provider evals

`@flue/opentelemetry` projects Flue runtime observations into the OpenTelemetry GenAI semantic conventions pinned at commit `4c8addb53718b544134be47e256237026fe88875`.

Vercel AI SDK inference and loop adapters for @aevr/agents.

HuggingFace Inference API connector for BonkLM - Model input/output validation

Heroku CLI plugin for Heroku AI add-on

PostgreSQL-native workflow engine for defining, managing, and tracking DAG-based workflows directly in your database.

React Native binding of llama.cpp

Agent memory for LLM agents: FSRS spaced repetition, Hebbian learning, Ebbinghaus forgetting curves, emotional tagging, sleep consolidation and 15 more. ZenBrain's algorithm core — 20 modules, zero-dependency TypeScript library.

Bare-only in-process core of the QVAC SDK. Runs inference directly on the Bare runtime with explicit plugin assembly and no RPC, worker, or subprocess layer.

Provider-agnostic inference runtime with Anthropic, OpenAI, and Google GenAI adapters

AI runtime for agent-driven products — agents, memory, LLM providers (Inference Snaps, Ollama, OpenAI-compatible), tools, and orchestration. Anthropic-SDK-free.

The exhaustive Pattern Matching library for TypeScript.

TypeScript SDK and CLI for Morph Fast Apply integration

Pi provider adapter for workstation inference with lifecycle-read-only text paths and scheduler-claimed one-shot audio dispatch.

Multi-arch builds of HuggingFace tokenizers

Vite plugin to transform SVGs into React components