memorylane
MemoryLane provides persistent memory and context for AI agents, enabling semantic recall, session history, and memory management via CLI, API, SDK, and MCP.
README
MemoryLane
MemoryLane gives AI agents durable context.
Agent-native memory layer for persistent context, semantic recall, session history, SDK, CLI, API, and MCP.
Install
npm install -g @talocode/memorylane
Or run directly:
npx @talocode/memorylane demo
Quick Start
# Save a memory
memorylane remember "User prefers short, direct X posts" --tag writing --tag preference
# Recall it later
memorylane recall "How should I write X posts?"
# Search memories
memorylane search "Talocode"
# List everything
memorylane list
# Run interactive demo
memorylane demo
CLI
memorylane --version
memorylane --help
# Core commands
memorylane remember <text> [--tag ...] [--importance N] [--session id]
memorylane recall <query> [--limit N] [--tags ...]
memorylane search <query> [--limit N] [--tags ...]
memorylane list [--limit N] [--tag ...]
memorylane get <id>
memorylane delete <id>
memorylane clear --yes
# Sessions
memorylane sessions create --title "My Session"
memorylane sessions list
memorylane sessions show <sessionId>
# Import/Export
memorylane export --out export.json
memorylane import export.json
# Server
memorylane serve --port 3040
# MCP
memorylane mcp
# Diagnostics
memorylane doctor
memorylane demo
API
Start the server:
memorylane serve --port 3040
Endpoints
| Method | Path | Description |
|---|---|---|
| GET | /health |
Health check |
| GET | /v1/memorylane/health |
API health check |
| GET | /v1/memorylane/capabilities |
List available endpoints |
| POST | /v1/memorylane/memories |
Save a memory |
| GET | /v1/memorylane/memories |
List memories |
| GET | /v1/memorylane/memories/:id |
Get a memory |
| DELETE | /v1/memorylane/memories/:id |
Delete a memory |
| POST | /v1/memorylane/recall |
Recall memories |
| POST | /v1/memorylane/search |
Search memories |
| POST | /v1/memorylane/sessions |
Create a session |
| GET | /v1/memorylane/sessions |
List sessions |
| GET | /v1/memorylane/sessions/:id |
Get session with memories |
| POST | /v1/memorylane/export |
Export all data |
| POST | /v1/memorylane/import |
Import data |
Example
curl -X POST http://localhost:3040/v1/memorylane/memories \
-H "Content-Type: application/json" \
-d '{"text": "User prefers short posts", "tags": ["writing", "preference"], "importance": 8}'
curl -X POST http://localhost:3040/v1/memorylane/recall \
-H "Content-Type: application/json" \
-d '{"query": "How should I write?", "limit": 5}'
SDK
import { MemoryLaneClient } from "@talocode/memorylane";
const memory = new MemoryLaneClient({ baseUrl: "http://localhost:3040" });
await memory.remember({
text: "User prefers short posts",
tags: ["writing", "preference"],
importance: 8,
});
const results = await memory.recall({
query: "How should I write?",
limit: 5,
});
MCP
Add to your MCP config:
{
"mcpServers": {
"memorylane": {
"command": "memorylane",
"args": ["mcp"]
}
}
}
Available tools: memorylane_remember, memorylane_recall, memorylane_search, memorylane_list_memories, memorylane_create_session, memorylane_list_sessions, memorylane_export, memorylane_import.
Cloud Auth
Local usage is open-source and keyless. For Talocode Cloud API access, set:
export TALOCODE_API_KEY="your-key"
export MEMORYLANE_CLOUD_MODE=true
Install Options
- npm:
npm install -g @talocode/memorylane - npx:
npx @talocode/memorylane - Linux/macOS:
curl -fsSL https://raw.githubusercontent.com/talocode/memorylane/main/install.sh | bash - Windows:
iex ((New-Object System.Net.WebClient).DownloadString('https://raw.githubusercontent.com/talocode/memorylane/main/install.ps1')) - Android (Termux):
pkg install nodejs && npm install -g @talocode/memorylane
Examples
See the examples directory:
Docs
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.