Search

A Python SDK that enables developers and LLMs to seamlessly interact with multiple blockchain networks through a unified, chain-agnostic interface.

Minimal LLM router with multi-model fallback chain. Zero dependencies. Works in CF Workers, Lambda, Node.js.

n8n node for Cloudflare D1 Manager Worker API - Manage D1 databases with select, insert, update, delete, and more

Find, download (over BitTorrent + webseeds), and SHA-256-verify LLM models from the LLM Torrents catalog.

SDK Python officiel d'AI Forge ESPRIT — un enrobage fin du SDK OpenAI.

PostQueen community node for n8n (fork of n8n-nodes-postiz)

n8n community node for TranscriptFetch - video transcripts from YouTube, TikTok, Instagram, X & Facebook, plus any web page as clean Markdown.

Provider-agnostic object storage (S3, Cloudinary, Google Cloud, Azure Blob, MinIO).

Openai plugin for Corsair

n8n workflow importer for Pikku — converts n8n exports into Pikku workflow graphs, agents and stub functions

The OpenAI backend module for the qeta plugin.

LangChain wrapper for tokz: compresses ToolMessage content in place before every model invoke/stream, with zero code changes.

OpenAI SDK wrapper for tokz: compresses tool results in place before every chat.completions call, with zero code changes.

A powerful yet simple library to build your own AI applications.

n8n node for controlling CloakBrowser over CDP with native CloakBrowser humanization

OpenAI-compatible language model adapter for Pilot (Ollama, OpenAI, OpenRouter, and similar endpoints).

Lightweight semantic cache for LLM and RAG pipelines. One class, one method, zero required dependencies, sync and async.

Companion plugin: load & serve pre-quantized humming Qwen-Image DiT pipelines on stock vLLM-Omni

Governed structured-output LLM pipeline: rate limit → spend caps (per-user + global circuit breaker) → cache → provider-chain failover → Zod validation → usage logging → LLM-judge, with a deterministic mock provider for CI.

Durable BullMQ-backed event bus adapter for Slingshot