
Agent Memory Mcp
- 558 installs
- 29.9k repo stars
- Updated July 27, 2026
- davila7/claude-code-templates
agent-memory-mcp is a Claude Code skill that runs a persistent MCP memory bank so agents can search, write, and tag architecture patterns and decisions across sessions for developers building long-running AI coding workf
About
Agent Memory MCP is an integration skill that boots a searchable, persistent memory server for AI coding agents. developers shipping agent-heavy products use it in Build to stop re-explaining architecture every session. Setup clones the agentMemory repo into the skills workspace, installs Node dependencies, compiles, and starts the MCP server scoped to a project id and absolute workspace path. Exposed tools let the agent query prior patterns (“authentication”) and record new decisions with structured types and tags. The model fits multi-week builds and later Operate work where prior decisions must stay discoverable. It requires local Node tooling and comfort running MCP alongside your editor. It complements ad-hoc markdown notes by making memory machine-retrievable through standard MCP calls rather than brittle copy-paste context.
- Hybrid memory system synced with project documentation via MCP tools
- memory_search by query, type, and tags; memory_write for keys, types, content, and tags
- Node 18+ workflow: clone, npm install, compile, start-server with project id and workspace path
- Typed knowledge: architecture, patterns, and decisions for cross-session retrieval
Agent Memory Mcp by the numbers
- 558 all-time installs (skills.sh)
- +11 installs in the week ending Jun 23, 2026 (Skillselion tracking)
- Ranked #1,635 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: HIGH risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davila7/claude-code-templates --skill agent-memory-mcpAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 558 |
|---|---|
| repo stars | ★ 29.9k |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How do coding agents persist memory across sessions?
Run a persistent MCP memory bank so agents can search, write, and tag architecture patterns and decisions across sessions.
Who is it for?
Engineers running multi-session agent workflows who need searchable, tagged memory for architecture patterns and decisions beyond chat context windows.
Skip if: Single-shot code generation tasks, teams without Node.js v18+, or projects satisfied by README and ADR files without MCP infrastructure.
When should I use this skill?
A developer wants persistent agent memory, MCP search/write for patterns and decisions, or cross-session architecture recall with agentMemory.
What you get
MCP memory server, tagged architecture/pattern/decision records, searchable long-term agent knowledge, and synced project documentation.
- MCP memory server
- tagged decision records
By the numbers
- Requires Node.js v18+
Files
Agent 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
1. Clone the Repository: Clone the agentMemory project into your agent's workspace or a parallel directory:
git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory2. Install Dependencies:
cd .agent/skills/agent-memory
npm install
npm run compile3. 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
Related skills
How it compares
Use agent-memory-mcp for MCP-backed cross-session agent recall; use markdown ADR files alone when teams do not run an MCP server.
FAQ
What are the prerequisites for agent-memory-mcp?
agent-memory-mcp requires Node.js v18 or newer. Developers clone the agentMemory repository into .agent/skills/agent-memory, install dependencies, and run the MCP server for read, write, and search.
What knowledge does agent-memory-mcp store?
agent-memory-mcp stores persistent, searchable long-term memories tagged by architecture patterns and decisions. The hybrid system syncs with project documentation so agents recall prior choices across sessions.
Is Agent Memory Mcp safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.