Search

n8n community node for Komplex AI — a hallucination detector for LLM output.

Claude Code の読み上げ用に、要約と音声合成を担うローカル常駐サーバー

A local web UI to manage multiple Claude Code profiles: move projects and memories between them, share skills, edit settings, undo anything.

Temporary package placeholder for staged publishing

Provider-neutral LLM service interface for the Hydra harness

Beluga: a fast reader for random-over-time, dense-over-space weather data (zarr v2/v3, Beluga v0) from blob storage, for ML training

Domain data form (ctx.storage.domain): schema-validated, event-emitting KV domains over storage backends for the Hydra harness

Storage hub (ctx.storage): named backend registry plus mounted data-form facilities for the Hydra harness

DeepSeek chat-completions adapter for the Hydra harness LLM seam

Files on local disk, in memory or in object stores, behind one async interface.

Standardized admission control for LLM inference

Provider-routed LLM request retry policy for the Hydra harness

Native account authorization for provider subscriptions

Session-local model call identity, timing, and tool diagnostics

pi-ai-backed DeepSeek adapter for the Hydra harness LLM seam (design-verification twin of hydra-llm-deepseek)

n8n community node for the LiteLLM proxy management API: virtual keys, teams, users, models and spend

Terraform module that creates a kind cluster and installs the RagLeap Helm charts, tested on a real cluster

Generate images and video from Python on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2, GPT Image 2.5 and more with one API key

OpenAI provider plugin for BionicJS

Envio de documentos ao RAG do BoxAI, inclusive muito grandes: chunker determinístico em stream (corte UTF-8 seguro, ids estáveis, sobreposição, metadados herdados), contrato com ACL obrigatória validada no cliente e cliente de ingestão com partes retomáve