Search

Oriora as a Vercel AI SDK provider — best model per request, routed on your own vendor keys (BYOK). OpenAI-compatible.

LedgeLM evaluation helpers for LangChain runnables and models

GPTFuzzer jailbreak optimizer for superred

PoisonedRAG knowledge-corruption optimizer for superred

Vercel AI SDK wrapper for tokz: compresses tool results in place, compacts history, and expands on reference.

Amazon DynamoDB Storage backend for Strands Agents — reserved, initial release coming soon.

n8n node for Microsoft Graph HTTP requests using multi-tenant client assertion authentication.

Domain-agnostic Retrieval-Augmented Generation (RAG) engine core library

Python SDK for LLMSafeSpaces API

Composable React UI for tools and connectors.

n8n node for propzapi, the props-first sports odds API. Pull player props, game odds, fixtures and live scores as clean JSON.

Self-evolving librarian agent on Pi framework with pluggable retrieval methods

TokenSpeed is a speed-of-light LLM inference engine.

Native macOS voice companion, Node.js client, CLI, tools, and browser bridge for GPT Realtime.

LangChain-based OpenAI-compatible translation provider for ai-i18n.

Vercel AI SDK provider for PleumRouter — one key, OpenAI-compatible access to 238 models, with cache-skip / user / tags headers.

AI SDK UI Message Stream adapter for Agentic Chat UI.

LLM gateway traffic profiler: prefix-reuse analysis, cache-hit-rate upper bounds, and anonymized replayable trace export

LangChain.js document loader for Xberg document extraction (placeholder release).

AI SDK LanguageModel fulfilled through the Agent Provider extension.