Search

Toggle OpenAI GPT-5.6 models between pi's 272K default context window and OpenAI's 1.05M maximum.

OpenAI-compatible LLM, structured prompt, scheduler, and memory APIs for tketool

Fill existing PDF forms — including scanned and flattened ones — from n8n data, using a layout you set up once at justfill.app

Native SuperGrok / X Premium OAuth provider for DeepSeek Harness. Reuses local grok-bridge tokens; no xAI API key.

Ankhorage dependency update policy and automation powered by Renovate.

Production-oriented Vision-Language engineering with CLIP, Qwen3-VL, visual document understanding and multimodal RAG.

SFTP provider package for Storage Kernel.

Local filesystem provider for Storage Kernel.

GCP Storage provider package for Storage Kernel.

Dragonfly extension for export to IES-VE GEM file format

Official Rasputin AI SDK for Elysia.

The s3-storage Plugin: adds S3 file upload (AWS SDK v3 + multer-s3) to a generated express-ts project.

Replay LLM plugin: short-circuits llm/stream with model chunks reconstructed from a recorded session JSONL (keyless snapshot tests)

n8n community node package for executing private workflows via the NodeFlex SignalR hub

LLM inference node distributed over Pear. Installs over P2P and updates itself over OTA.

Pragma command-line interface

Runtime-local LLM route capability declarations for DeepSeek Harness integrations.

Git-diff-aware security impact analysis: builds a dependency subgraph around changed code and optionally scans it for vulnerabilities with an LLM.

ChatGPT Codex subscription usage in the pi footer — multi-bucket limits, reset credits, consume action, /codex-usage report. Unofficial, not affiliated with OpenAI.

Fast, safe web search and content retrieval for LLM applications