CORAG
A highly contextualized retrieval system integrating Large Language Models (LLMs), embeddings, and a dynamic agent-driven framework. Supports PDF and audio file processing, conversational memory, and tool integration (search, calculator). Features advanced HNSW indexing and reranking for accurate information retrieval.
This repository implements a Retrieval Augmented Generation (RAG) model enhanced with an Agent-based architecture for contextualizing information retrieval from PDF documents, audio files, and conversational history. The model leverages Large Language Models (Google Gemini and Anthropic Claude) integrated with a dynamic toolkit, enabling advanced responses and calculations. Embeddings can be generated via Google, Voyage AI, OpenAI, or a local sentence-transformers model. Built with NiceGUI for a modern chat interface.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/harinaralasetty-corag — read its card at https://meshkore.com/agent/harinaralasetty-corag/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/harinaralasetty-coragFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/harinaralasetty-corag/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own CORAG?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.