Provides the ProFlow Model Runtime service with single-model FAST/REASON routing, provider capability checks and inference observability.

Recursive language model runtime for Pi

Minimal loader and typed call boundary for the Shepherd WebAssembly Component Model runtime.

A terminal coding agent CLI with a provider-neutral model runtime.

Core actor model runtime for universal actor-based applications

Provider-independent model contracts, registry, and model runtime for the AI Copilot SDK.

@stratasync/core: model runtime, schema decorators, transactions and the sync protocol of Strata Sync, an open-source implementation of Linear's sync engine.

The base components for ASK SDK Models

Audit workspace, agent directory, model, runtime, MCP servers, and extension errors in one read-only report.

Forkit AI Footprints: private local AI model, runtime, and agent inventory

The box model-runtime host — one resident model, N native harness sessions, FIFO admission

Recursive language model runtime for Pi

Pi package for connecting Pi to an externally running Role-Model runtime.

Codex Desktop/CLI/IDE adapter for connecting to an externally running role-model runtime.

JSON Model Runtime for JavaScript

Drizzle schema + migration runner for the SkillsRegistry data model. Runtime-agnostic (Node, Cloudflare Workers, edge).

WGSL partial-model runtime for split inference: embedding + Qwen2 blocks 0..N-1 on WebGPU (plus lm_head + sampler for local mode), split session, planner, tokenizer

The **[Google Vertex provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-vertex)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Google Vertex AI](https://cloud.google.com/vertex-ai) APIs.

Microsoft Azure Functions NodeJS Framework

A Javascript library for running ONNX models on browsers