Inspect Parquet metadata, encodings, compression, indexes, and Bloom filters locally
-
Updated
Jul 30, 2026 - Python
Inspect Parquet metadata, encodings, compression, indexes, and Bloom filters locally
Hands-on tutorial for the Agentic Resource Discovery (ARD) protocol, with a runnable two-organization data-analytics example over ClickHouse.
Neutral self-hosted registry and toolkit for Agentic Resource Discovery.
Agent-only x402 service for signed exact-commit evidence on public Agent Skills
Plugin marketplace for AI-native development agent skills
Build, validate, discover, and resolve ai-catalog.json files for the Agentic Resource Discovery (ARD) spec. TypeScript, zero runtime deps.
Data-agnostic Agentic RAG with hybrid BM25, Chroma, and Neo4j retrieval, source verification, bounded retries, and AWS ECS deployment.
A typed coherence layer for portable organizational AI agents.
Preview ARD / AI Catalog readiness tools for agent-operable apps, APIs, docs, and workflows.
The open marketplace protocol for agent-to-agent compute
Agentic Resource Discovery (ARD) is a proposed open standard for the discovery layer that sits in front of every agentic protocol — the step before invocation, where a client asks "what is available for this task?" and gets back a ranked set of MCP servers, agent cards, skills, workflows and APIs it could use.
Add a description, image, and links to the agentic-resource-discovery topic page so that developers can more easily learn about it.
To associate your repository with the agentic-resource-discovery topic, visit your repo's landing page and select "manage topics."