
Agent Memory
FreePersistent memory management for AI agents.
Free · Opens the source repo
What Agent Memory does
The Agent Memory skill provides a robust solution for AI agents needing a persistent and searchable memory bank. This skill is designed to automatically sync with project documentation, ensuring that all critical knowledge is readily accessible. By running as an MCP server, it facilitates efficient reading, writing, and searching of long-term memories, making it a valuable tool for developers and designers alike.
With this skill, users can utilize several key functions, including memory search, memory write, and memory read. The memory_search function allows for querying memories based on specific criteria, such as type or tags, making it easy to retrieve relevant information. The memory_write function enables users to record new knowledge or decisions, ensuring that important insights are documented for future reference. Additionally, the memory_read function allows users to retrieve specific content by key, streamlining the process of accessing stored information.
The skill also provides analytics through the memory_stats function, giving users insight into their memory usage. Furthermore, it includes a standalone dashboard that visualizes memory statistics, which can be accessed via a local server. This feature enhances the user experience by providing a clear overview of memory management and usage.
Overall, the Agent Memory skill is tailored for developers and designers who require a structured approach to knowledge management within their projects. By integrating this skill, users can enhance their workflow efficiency and ensure that critical information is always within reach.
When to use it
Use this skill when you need to maintain a persistent memory for your AI agent, especially in projects with extensive documentation and decision-making processes.
When not to use it
This skill may not be suitable for simple projects where memory management is not required or for users who prefer not to manage persistent data.
What you can build with it
Managing Complex Projects
In large-scale projects, the Agent Memory skill helps maintain a clear record of architectural decisions and patterns.
Collaborative Development
Teams can utilize the memory bank to ensure everyone has access to the same knowledge base, reducing miscommunication.
Documentation Sync
Automatically syncing with project documentation allows for seamless updates to the memory bank, keeping it relevant.
How to install Agent Memory
View source1. Install with the skills CLI
npx skills add davila7/claude-code-templates/agent-memory-mcp --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by davila7Agent Memory Skill
This skill provides a persistent, searchable memory bank that automatically syncs with project documentation. It runs as an MCP server to allow reading/writing/searching of long-term memories.
Prerequisites
- Node.js (v18+)
Setup
-
Clone the Repository: Clone the
agentMemoryproject into your agent's workspace or a parallel directory:git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory -
Install Dependencies:
cd .agent/skills/agent-memory npm install npm run compile -
Start the MCP Server: Use the helper script to activate the memory bank for your current project:
npm run start-server <project_id> <absolute_path_to_target_workspace>Example for current directory:
npm run start-server my-project $(pwd)
Capabilities (MCP Tools)
memory_search
Search for memories by query, type, or tags.
- Args:
query(string),type?(string),tags?(string[]) - Usage: "Find all authentication patterns" ->
memory_search({ query: "authentication", type: "pattern" })
memory_write
Record new knowledge or decisions.
- Args:
key(string),type(string),content(string),tags?(string[]) - Usage: "Save this architecture decision" ->
memory_write({ key: "auth-v1", type: "decision", content: "..." })
memory_read
Retrieve specific memory content by key.
- Args:
key(string) - Usage: "Get the auth design" ->
memory_read({ key: "auth-v1" })
memory_stats
View analytics on memory usage.
- Usage: "Show memory statistics" ->
memory_stats({})
Dashboard
This skill includes a standalone dashboard to visualize memory usage.
npm run start-dashboard <absolute_path_to_target_workspace>
Access at: http://localhost:3333
Frequently asked questions about Agent Memory
Similar skills
Build MCP Server
Streamline your MCP server development with guided discovery.
MCP Server Development Guide
Build high-quality MCP servers for LLM integration.
NemoClaw Documentation Access
Streamline your access to NemoClaw documentation with AI agents.
Azure AI Gateway
Manage AI models and tools with Azure API Management.
Agent Connect
Seamlessly connect agents to external APIs and services.
OpenAPI to MCP
Transform OpenAPI specs into MCP servers effortlessly.
