Search

AIPerf is a package for performance testing of AI models

FastAPI backend & desktop launcher for running local models via llama.cpp

Security-hardened fork of n8n-nodes-globals — global constants node for n8n

Custom n8n nodes for ShopfloorGPT Roadrunner — agent invocation and document upload

n8n community node for the Weclapp ERP/CRM platform

Open-source CLI for semantic Taiwan legal judgment retrieval — search judgments, package them for your own AI tools, and run a bundle-level citation check. Retrieval-only; does not generate or endorse legal advice.

n8n community node for Warmy.io email warmup API

n8n community node for the Ngram public API: create videos, watch for completion, and look up video status from n8n workflows.

Reasoning-aware context runtime for RAG — chunk, retrieve, and allocate the document context an LLM should see, with citations and a Decision Report. In-process, no vector DB.

Ultra-fast LLM inference engine with a Vulkan compute backend

An LLM wrapper built for scene prog projects

An LLM based program synthesizer for custom DSLs

Deterministic identity + privacy layer for LLM applications

Allows to gather consumed products on daily basis

Mind-as-observer probe — ship Claude Code (and other external) conversations into your thinqOS Mind.

The CockroachDB Vector Embedding Toolkit is a developer-focused set of tools for generating, storing, and querying vector embeddings directly within existing CockroachDB tables. It enables prototyping similarity search and AI-backed workflows without the need for a separate vector database or complex architectural changes.

Compressed vector index for RAG pipelines — 7-10x storage reduction, no training required

Reversible UUID/ID aliasing for LangChain & LangGraph — cut tokens and stop the LLM mangling your IDs.

Disk-backed Storage adapter for Causeway — dev + tests.

Keeper Secrets Manager SDK storage integration with Google Cloud KMS for encrypted key-value storage.