Reusable AI skills and capabilities for agent workflows
1qh
The RAG engine minus the store: multi-engine document understanding with per-page routing, chunking, provenance that survives chunking, embedding, and retrieval logic.
...moreGitHub Actions
n8n community node to receive events dispatched by the ASAPIO Integration Add-on (Event Studio)
Astral.Soft
Skills: - [caveman](#caveman) - [unit-testing](#unit-testing) - [styling](#styling)
GitHub Actions
n8n community node for verified German company data: KYB company profiles (Handelsregister, VIES VAT, Bundesanzeiger), insolvency register checks and Impressum contact extraction — powered by Apify actors.
...moreAI ROUTER contributors
Normalize OpenAI-compatible API failures, plan conservative retries, redact logs, and inspect SSE streams
MZero Team <[email protected]>
Zero-Configuration RAG Framework and Embeddable SDK for Python
usetheodev
Open-source RAG (Retrieval-Augmented Generation) engine for the Theo ecosystem. Pre-release.
x12i
Download a URL with a real (headless) browser and convert it to clean Markdown, producing the FetchResult that @x12i/core parsers consume.
...moreTodd Thomson
The LLM stack you can read and understand: Gemma 4 and Llama on CUDA, built from explicit C++23 components.
Neongecko
None
OpenAI
TypeScript SDK and CLI for Codex Security
darko893
n8n node for Haunt web extraction: structured data from any public page with honest failure codes
Lucas Monteverdi
A from-scratch CLI evaluation framework for RAG pipelines.
nichham2
n8n community node to install, list, and remove system fonts on the n8n server — supports Google Fonts, direct URL, and Base64 input
...moreMiska Kankkonen
Probabilistic Python objects: invent attributes, methods, anything out of thin air. An LLM fills the silence, every answer carries confidence, and written code always wins.
...moreSameed Khalid <[email protected]>
Document preprocessing toolkit for RAG and LLM pipelines: text cleaning, chunking strategies, metadata extraction, and token counting.
...moreGitHub Actions
Loopback Anthropic-Messages-API proxy that validates and repairs tool-call responses in flight, routing across multi-provider LLM backends.
...moretellerlin
AgentBOM LangChain adapter
Risheek kumar B <[email protected]>
A practical PRAGMA model implementation for tokenized tabular event histories
GitHub Actions
LlamaIndex.TS reader and node parser for Xberg — extract text, tables, metadata, and structure-aware nodes from 90+ document formats with optional OCR.
...moreAadhya <[email protected]>
A lightweight Python decorator for caching, rate limiting, and retrying LLM API calls.
GitHub Actions
Streaming prompt and ordered tool-call executor for Clear Ideas Agent Runtime.
GitHub Actions
n8n community node to validate input data against a JSON Schema (ajv)
rudrendu_paul_packages
Zero-dependency, cross-platform LLM/GEO/AEO checker CLI — 21 technical-SEO and generative-engine-optimization checks, no headless browser, no Python interpreter required.
...more