llama addon for qvac

Self-Optimizing Neural Architecture (SONA) - Runtime-adaptive learning with LoRA, EWC++, and ReasoningBank for LLM routers and AI systems. Sub-millisecond learning overhead, WASM and Node.js support.

Tensorflow model converter for javascript

The **[Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/index)** for the [Vercel AI SDK](https://ai-sdk.dev/docs) contains language model support for thousands of models through multiple inference providers via the Hugging

A type inference plugin for ESDoc [PoC]

Describe binary structures with full TypeScript support. Encode and decode into pure JavaScript objects.

End user conduit agent for connecting local LLMs to the cloud.

OpenClaw provider for managed and external llama.cpp servers

AI inference primitives: provider-agnostic text generation clients for Anthropic and Ollama

The modular and type safe schema library for validating structural data

HuggingFace Inference API provider for @workglow/ai.

CAVE probabilistic layer — Bayesian fusion of numeric estimates, noisy-AND conditional confidence, hypothesis helpers.

The SDK is used to run image inference with the Runware API, powered by the RunWare inference platform. It can be used to generate imaged with text-to-image and image-to-image. It also allows the use of an existing gallery of models or selecting any model

OpenVINO™ Runtime for Node.js: high-performance deep learning inference on Intel CPU, GPU, and NPU.

An implementation of a Bayesian-approximation based game ranking system described by Weng and Lin and used by HackerRank.

Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, tamper-evident audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode

VTX Macro CLI, MCP server, and durable external inference host.

ReScript's new standard library. Intended to be familiar for JavaScript developers, easy to use, and be rich enough (without being bloated) so that you don't need to reach for anything else for typical ReScript development.

A native Capacitor plugin that embeds llama.cpp directly into mobile apps, enabling offline AI inference with chat-first API design. Complete iOS and Android support: text generation, chat, multimodal, TTS, LoRA, embeddings, and more.

Conform helpers for integrating with Zod