Nate Aune natea

Claude Memory Template

Copy-Paste Instructions for Optimal AI Interaction

⸻

1. Core Identity and Objective

I am [Your Name/Role], focused on:

AgentDB

A sub-millisecond memory engine built for autonomous agents

Claude Flow treats memory as the backbone and MCP tools as the hands. You get concurrent agents that coordinate cleanly, keep context tight, and ship durable artifacts without dragging long text through prompts. It feels like an ops layer for intelligence.

The stack is simple. Claude Code as the client. Claude Flow as the MCP server. SQLite memory at .swarm/memory.db for state, events, patterns, workflow checkpoints, and consensus. Artifacts hold the big payloads. Manifests in memory link everything with ids, tags, and checksums.

Coordination is explicit. Agents write hints to a shared blackboard, gate risky steps behind consensus, and record every transition as an event. Hooks inject minimal context before tools run and persist verified outcomes after. Small bundles in, durable facts out.

Planning keeps runs stable. Use GOAP to sequence actions with clear preconditions. Use OODA to shorten loops.

Observe metrics, orient with patterns, decide through votes, act with orchestration. Topology adapts from hi

Appendix: Technical Details for ChatGPT App UI

A. Rendering model

Components render inside a sandboxed iframe managed by ChatGPT.
Your MCP tool returns data plus UI metadata that the Apps SDK interprets to mount your component.
The host injects a window.openai bridge into the iframe for props and events. ([OpenAI][1])

B. Component contract

📚 Complete Tutorial: Building Neural Document Classification with Flow Nexus & Claude Flow

The tutorial walks through the full process:

Preprocessing pipeline in a sandbox with tokenization and embeddings
Mesh-based neural cluster with proof-of-learning consensus
Validation agents enforcing input gates, scope checks, and quality rules
Dual-model comparison against TensorFlow.js vs Flow Nexus
Weighted ensemble voting for 90%+ classification accuracy
Half the value is speed, the other half is traceability. You’re not just training a model, you’re building a production pipeline with verification and cost controls baked in.

And it scales, you can run batch classification, deploy an API endpoint, and monitor real-time performance metrics without leaving the Flow Nexus environment.

Complete Step-by-Step Guide for Deploying Complex Multi-Agent Applications

Based on the successful deployment of the Swarm Stock Trading Application

🏥 Dr House - Brutal Honest Assessor v2.0

Created by: Bradley Ross linkedin.com/in/bradaross/
Version: 2.0 Gold Standard
Optimized for: Claude Code CLI (works with standard CLI)
License: Apache 2.0
Acknowledgements: Thank you Ruv, Bron, Agentics Foundation

Click here for Agent Code Github agent code

ÆGENTIC-TAXONOMY-FRAMEWORK: A publicly proposed model and framework to capture, convey and optimally align the explicit meanings, intentions, capabilities, potential, and more, through AGENT-based ecosystems.

AN ÆGENTIC TAXONOMICAL FRAMEWORK & CLASSIFICATION SYSTEM

Apply this framework to any Class in our AGENT‑TAXONOMY (Command → OMNIÆNCE) by setting {Class} accordingly.

Claude-SPARC Automated Development System For Claude Code

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

The SPARC Automated Development System (claude-sparc.sh) is a comprehensive, agentic workflow for automated software development using the SPARC methodology (Specification, Pseudocode, Architecture, Refinement, Completion). This system leverages Claude Code's built-in tools for parallel task orchestration, comprehensive research, and Test-Driven Development.

	{
	"env": {
	"CLAUDE_FLOW_AUTO_COMMIT": "false",
	"CLAUDE_FLOW_AUTO_PUSH": "false",
	"CLAUDE_FLOW_HOOKS_ENABLED": "true",
	"CLAUDE_FLOW_TELEMETRY_ENABLED": "true",
	"CLAUDE_FLOW_REMOTE_EXECUTION": "true",
	"CLAUDE_FLOW_CHECKPOINTS_ENABLED": "true",
	"AGENTDB_LEARNING_ENABLED": "true",
	"AGENTDB_REASONING_ENABLED": "true",