Search

Diagnose vector search problems in RAG/LLM systems. Hunt down why retrieval fails — embedding quality, vector search, BM25, reranker analysis.

Antigravity proxy for AI SDK.

Free multi-provider AI SDK — drop-in OpenAI & Anthropic compatibility with 27 free providers

Cached LLM client with Ollama + Anthropic provider dispatch, fixture mode, and JSON-schema-strict completions.

n8n node to call WebScraping.AI API services - LLM-powered web scraping with JavaScript rendering and proxies.

Full-featured document parsing node for n8n — PDF, DOCX, XLSX, PPTX, images, OCR, markdown output. No native dependencies.

JavaScript/TypeScript SDK for Larkup RAG servers

Local-first, top-tier RAG over your notes, docs, and PDFs — answered by Claude.

Local-first semantic document search CLI — indexes your documents and finds them by meaning, not keywords. No cloud. No API keys.

A NestJS module that provides decorators and utilities for defining LLM (Large Language Model) function calling tools using TypeScript decorators. This library enables you to easily expose NestJS service methods as structured tools that can be used with L

Gateway-agnostic core for llm-catalog: config schema, resolver, GatewayTransport, and LiteLLM codegen. Knows nothing about any runtime adapter.

Consolidated AI-powered model recommendation CLI for OpenCode OMO agent configurations

Storage utilities for ServerKit.

n8n node for GeoMaps — create, update, delete and find records (map pins) on a CSV/Excel data source.

Agentic memory for Pi — verbatim session capture + grep retrieval

Cloud-Dog AI platform storage library — storage backends plus PS-94 transfer helpers

LangChain integration for ZeroEntropy zerank rerankers

LangChain adapter for Snubber

Zero-dependency helpers to harden LLM prompts against injection from untrusted third-party text.

An intelligent tool-making package that leverages LLMs to analyze projects and generate tools