light-agent-memory-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@light-agent-memory-mcp-server remember that I prefer pnpm for package management"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
light-agent-memory-mcp-server
MCP server for persistent agent memory — projects, preferences, and session learnings stored in a local SQLite database.
Harness-agnostic. Works with any MCP-compatible client: opencode, Claude Desktop, Cursor, Windsurf, etc.
Install
npm install -g light-agent-memory-mcp-serverOr use directly with npx (no install needed):
npx light-agent-memory-mcp-serverRelated MCP server: apex-memory
Configure
Add to your MCP client's config:
opencode (~/.config/opencode/opencode.json):
{
"mcp": {
"memory": {
"type": "local",
"command": ["npx", "-y", "light-agent-memory-mcp-server"],
"enabled": true
}
}
}Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "light-agent-memory-mcp-server"]
}
}
}Cursor (.cursor/mcp.json):
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "light-agent-memory-mcp-server"]
}
}
}Custom database path
npx light-agent-memory-mcp-server --db /path/to/custom.dbTools
Project Memory
Tool | Description |
| Save/update project context (tech stack, architecture, conventions) |
| Get project details by name |
| List all saved projects |
Preference Memory
Tool | Description |
| Save/update a personal coding preference |
| Get a preference by key |
| List preferences (optionally filtered by category) |
Learning Memory
Tool | Description |
| Record a session learning (solution, insight, bug note) |
| Search learnings by keyword |
Generic
Tool | Description |
| Unified save (auto-routes by type) |
| Cross-type search by keyword |
| Delete a memory by type and ID |
| List all memories with pagination and stats |
Examples
Save a project:
memory_project_save({
name: "my-app",
path: "/home/user/projects/my-app",
tech_stack: ["TypeScript", "React", "SQLite"],
architecture: "Monorepo with pnpm workspaces, plugin-based architecture",
conventions: "ESM-only, strict TypeScript, no comments in code"
})Save a preference:
memory_pref_save({
key: "language.typescript.style",
value: "Always use ESM imports, strict mode, and prefer readonly types",
category: "language"
})Record a learning:
memory_learning_save({
title: "Fix SQLite WAL mode deadlock",
content: "When using WAL mode in SQLite, set busy_timeout to 5000ms to avoid SQLITE_BUSY errors under concurrent reads.",
project_name: "my-app",
tags: ["sqlite", "debugging", "concurrency"]
})Search all memories:
memory_search({ query: "SQLite" })Database
Data is stored in ~/.agent-memory/memory.db by default (SQLite via Node.js built-in node:sqlite). The database is created automatically on first run.
Schema
projects —
id,name(unique),path,tech_stack(JSON),architecture,conventions,notes, timestampspreferences —
id,key(unique),value,category, timestampslearnings —
id,title,content,project_name,tags(JSON), timestamps
Development
git clone https://github.com/AliYar-Khan/light-agent-memory-mcp-server.git
cd light-agent-memory-mcp-server
npm install
npm run build
npm run dev # runs with tsx, no build stepLicense
MIT
Available Tools
12 toolsmemory_deleteDelete MemoryADestructiveIdempotent
Delete a specific memory by type and ID.
Inputs: id (required), type (required).
memory_learning_saveSave LearningA
Record a session learning — solutions discovered, bugs encountered, insights gained.
Inputs: title (required), content (required), tags, project_name.
memory_learning_searchSearch LearningsARead-onlyIdempotent
Search session learnings by keyword. Matches against title, content, and tags.
Inputs: query (required), limit, project_name.
memory_listList All MemoriesARead-onlyIdempotent
List all stored memories with optional type filter, pagination, and stats.
Inputs: type, limit, offset.
memory_pref_getGet PreferenceARead-onlyIdempotent
Retrieve a specific preference by key.
Inputs: key (required).
memory_pref_listList PreferencesARead-onlyIdempotent
List all saved preferences, optionally filtered by category.
Inputs: category.
memory_pref_saveSave PreferenceAIdempotent
Save or update a personal coding preference — style, tools, workflow patterns.
Inputs: key (required), value (required), category.
memory_project_getGet ProjectARead-onlyIdempotent
Retrieve saved context for a specific project by name.
Inputs: name (required).
memory_project_listList ProjectsARead-onlyIdempotent
List all saved projects.
Inputs: no named parameters.
memory_project_saveSave ProjectAIdempotent
Save or update project context — tech stack, architecture, conventions, and notes.
Inputs: name (required), path, notes, tech_stack, +2 more.
memory_saveSave MemoryA
Unified save — automatically routes to the correct table based on type. Use data fields matching the type: project (name, path, tech_stack, architecture, conventions, notes), preference (key, value, category), or learning (title, content, project_name, tags).
Inputs: data (required), type (required).
memory_searchSearch All MemoriesARead-onlyIdempotent
Search across all memory types by keyword. Optionally filter by type (project, preference, learning).
Inputs: query (required), type, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
The type-specific tools (project/pref/learning) are fairly distinct, but the generic memory_save, memory_search, and memory_list overlap with specialized equivalents like memory_project_save, memory_learning_search, and memory_project_list. The descriptions clarify the generic vs. specific distinction, but an agent still faces multiple paths to accomplish the same operation.
Tool names consistently use a memory_ prefix and mostly follow a memory_<type>_<action> pattern. Minor inconsistencies exist: 'search' is used for learning where 'list' or 'get' might be expected, and the top-level memory_save/memory_search/memory_delete/memory_list deviate from the type-specific naming pattern.
Twelve tools is reasonable for a memory system covering projects, preferences, and learnings. The count is slightly inflated by the generic memory_* tools that duplicate type-specific functionality, but overall the server remains well-scoped and navigable.
The server covers create, read, list, search, and delete across all memory types, either through type-specific or generic tools. Minor gaps exist—learning has no direct get-by-ID function, and deletion is only exposed through the generic memory_delete—but common workflows can be completed with existing tools.
Related MCP Connectors
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Related MCP Servers
- AlicenseCqualityBmaintenanceProvides persistent, local-first AI memory across sessions via MCP tools for storing, searching, and retrieving context from past interactions.31698 PyPI1MIT
- AlicenseNot gradedqualityDmaintenancePersistent memory for AI coding agents. Enables agents to save and recall decisions, patterns, bugs, and context across sessions via an MCP server with local SQLite storage.24 npm2MIT
- AlicenseAqualityCmaintenanceProvides persistent local memory for any MCP-compatible AI agent, enabling agents to store, search, recall, forget, export, and manage preferences, rules, and facts with zero dependencies, no cloud, and no API keys.8MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to persistently save, search, retrieve, update, link, and forget project-scoped memories through MCP tools, using local SQLite FTS5 keyword search without cloud access or telemetry.26 npm14MIT