AI Runtime — a provider-agnostic AI runtime and orchestration platform. Point it at whatever AI providers you have; it routes each task to the best available model. Ships the `ai-runtime` CLI and the `Runtime`/`AI` library API.

No description provided.

Core types and interfaces for Aegisora AI runtime governance platform.

AI runtime, providers, streaming, and framework adapters extracted from AbsoluteJS

Security analysis engine for Aegisora AI runtime governance.

n8n community node for Zscaler AI Guard (AI Runtime Security) API integration

Vercel AI SDK provider for the QVAC local AI runtime (chat, embeddings, transcription, translation, speech, OCR, image)

Unified AI runtime for ElsiKora modules

Aztrx AI — runtime stress-tester for web apps. Detect bugs, then prove them with an executable repro.

Checksum.ai test runtime

Reusable SOMA AI runtime: structured Host functions, knowledge-grounded assistant, and browser chat widget.

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

Senpi runtime plugin for OpenClaw

NEXUS AI — Local-first AI workstation CLI. Think, plan, execute — powered by local AI runtime.

Electron-first local AI runtime management with Node-safe llama-server launch utilities

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

LLM call loop + typed-trace recorder adapters for MetaObjects: provider-neutral LlmClient seam, callLlm bridge, Composite/Langfuse/OTel recorders.

AI runtime for KickJS — providers, @AiTool decorator, streaming, RAG, and agent loops

Public-safe runtime profile templates for AI client wrappers.

Application bootstrap: config-first startup, telemetry init, signal handling, graceful shutdown.