Agent-MemoryForge

🥈Silver

Agent-MemoryForge enables AI agents to retain and recall information across multiple modalities. Operations teams benefit from improved agent performance in tasks requiring historical context. It connects to Azure OpenAI and Neo4j for memory storage and retrieval.

139220Updated 1mo ago

Intermediate30min to implementautomation

Saves ~240 min per use

Quick InstallView Source

git clone https://github.com/hellangleZ/Agent-MemoryForge.git

Works with:

Claude

Overview

About This Skill

How to Use

[{"step":"Enable Agent-MemoryForge integration in your AI agent's configuration. In Azure OpenAI, set the 'memory' parameter to 'enabled' and configure the Neo4j connection string for persistent storage.","tip":"Use the Azure Portal to verify the integration is active. Check the 'Memory' tab in your agent's dashboard to confirm the Neo4j connection is established."},{"step":"Structure your interactions to include contextual information. When starting a new session, reference prior interactions using [PREVIOUS_INTERACTIONS] placeholder. For example: 'Based on our discussion yesterday about the Aurora microservice memory leak, let's continue...'","tip":"Use consistent terminology and identifiers (e.g., microservice names, cluster IDs) across interactions to improve memory retrieval accuracy."},{"step":"Leverage the 'Memory Update' section to explicitly store critical information. After resolving a task, summarize key takeaways and store them for future reference.","tip":"Prioritize storing actionable insights, pending tasks, and unresolved issues. Use tags or labels in Neo4j to categorize memories (e.g., 'bug-fix', 'deployment-plan')."},{"step":"Retrieve historical context when needed. Use the 'Context Summary' section to review prior interactions before addressing a new task. In Neo4j, query the 'AgentMemory' graph for related nodes.","tip":"For complex tasks, break down the problem into sub-tasks and query Neo4j for relevant memories before generating a response. This ensures continuity and reduces redundant work."},{"step":"Monitor memory usage and performance. Use Azure Monitor or Neo4j's query performance tools to track memory consumption and retrieval latency. Adjust the memory storage settings if performance degrades.","tip":"Set up alerts in Azure Monitor for high memory usage in the Neo4j instance. This helps identify potential bottlenecks in memory retrieval."}]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/hellangleZ/Agent-MemoryForge

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Act as an AI agent with persistent memory enabled by Agent-MemoryForge. When provided with [TASK_CONTEXT], [PREVIOUS_INTERACTIONS], and [NEW_INPUT], synthesize this information to generate a coherent response that demonstrates continuity with past interactions. Use the following format for your response: 

**Context Summary:** [2-3 sentence recap of prior relevant interactions]

**Actionable Insight:** [Specific recommendation or solution based on the combined context]

**Memory Update:** [What new information should be stored for future interactions?]

Input: [TASK_CONTEXT], [PREVIOUS_INTERACTIONS], [NEW_INPUT]

Example Output

{
  "Context Summary": "In our previous interaction on 2024-05-15, we discussed the performance issues of the 'Aurora' microservice in the 'Eclipse' cluster. The root cause was identified as a memory leak in the 'data-processor' container, which was consuming 95% of available memory. We implemented a temporary fix by restarting the container and increasing its memory limit from 2GB to 4GB.",

  "Actionable Insight": "The 'Aurora' microservice has been stable since the memory limit increase, but the underlying issue persists. The 'data-processor' container is now consuming 88% of its allocated 4GB memory, indicating the leak is still active but slower. I recommend scheduling a maintenance window to deploy the permanent fix (patch version 1.2.3) and monitoring memory usage for 24 hours post-deployment. The patch includes a garbage collection optimization that should reduce memory consumption by ~40%.",

  "Memory Update": "1. Aurora microservice memory leak persists but is controlled with 4GB limit. 2. Patch version 1.2.3 is ready for deployment. 3. Schedule maintenance window for 2024-05-22 at 02:00 UTC. 4. Monitor memory usage post-deployment for 24 hours. 5. Document the temporary fix in the runbook for future reference."
}