Search

Tiny RAG toolkit — chunking, embeddings abstraction, metadata, similarity search, and context building.

OpenCode plugin for OpenAI Responses API over WebSocket and HTTP SSE.

Local-first multilingual RAG for code and technical docs. In-process hybrid retrieval (vector + full-text) with FTS for Cyrillic and other non-ASCII scripts.

Official typed Python client for the NullMail temporary email Pro API

ANOLISA CLI — Agentic OS component lifecycle manager

Official Python SDK for LLMJury — run LLM experiments in production: deterministic variant assignment, prompt/model comparison, and non-blocking metrics tracking.

n8n community node for Status Check - Domain and email validation for workflow automation

Plug-and-play image generation & editing tools for opencode, powered by OpenAI gpt-image-2.

Serverless GraphRAG on DynamoDB — knowledge graph extraction, storage, and multi-hop traversal with zero infrastructure cost at rest.

Provides a llm command to ask for MongoDB query expressions in natural language, using Groq or any other local model (ollama)

An integration package connecting Sarvam AI and LangChain

TokenLab provider for Vercel AI SDK, built on the OpenAI-compatible provider.

n8n node for Feishu (Lark) Bot integration

n8n node for Pullbay API - App Store, Google Play, DuckDuckGo and more

It ain't langchain.

Privacy-first decentralized storage SDK with pluggable adapters

Custom LiteLLM providers for Pollinations.ai and AI Horde, two free image-generation APIs

Lightweight, Python-first model manager for local LLMs (the package manager for local AI models).

Domain-specific RAG embedding model for Data Science & ML documentation retrieval

LlamaIndex VectorStore for MySQL 9's native VECTOR type — works with ShannonBase, self-hosted MySQL, and MySQL HeatWave.