agrasandhany
Turns local plain-text notes into searchable long-term memory for AI agents through the MCP protocol.
README
AGrasandhanY
From Sanskrit agrasandhanī (uh-gruh-sun-DHAA-nee) — the mythic ledger that records every action of every soul.
agy — turn local notes into long-term memory for AI agents
Status: Alpha
What is Agrasandhany (agy)
Local, plain-text notes, written for yourself. That's the whole idea — and agy turns them into memory your agents can search over.
- Notes become memories — each file, turned into searchable facts.
- Folders become scopes —
projects/backend/design.mdis taggedprojects/backend, automatically. - Living summaries — a summary of notes by folder, auto-refreshed as they change.
vault (files) → daemon (sync) → Hindsight (memory)
↑
MCP (agents)
The filesystem is the source of truth — agy mirrors your files; it's not a backup. Delete a note and its memory clears on the next sync.
Under the hood: agy embeds Hindsight — a local retain/recall engine that extracts memories from your notes.
Prerequisites
- uv
- Linux or macOS (launchd auto-start requires macOS)
- An LLM provider — any Hindsight-supported provider works.
Install
git clone https://github.com/yugandhar-maram/agrasandhany.git ~/agrasandhany
cd ~/agrasandhany
Quick start (full guide)
# Configure LLM access
cp .env.example .env # defaults to Claude Code
export AGY_ENV_FILE=~/agrasandhany/.env
# Start the daemon
uv run agy daemon start
# Register a vault
uv run agy vault add ~/notes --name notes
# The daemon picks up new vaults automatically
MCP Integration
This gives your agent access to your memories. Add to your agent's MCP config (e.g. .claude/settings.json):
{
"mcpServers": {
"agrasandhany": {
"command": "uv",
"args": ["run", "--project", "~/agrasandhany", "python", "-m", "agy.mcp"],
"env": {
"AGY_ENV_FILE": "~/agrasandhany/.env",
"AGY_VAULT": "notes"
}
}
}
}
Docs
- usage — setup, daemon, vault, MCP
- configuration — env vars and vault settings
- operations — logs, jobs, troubleshooting
License
Dedicated to my wife — for the evenings, the weekends, and the patience. This wouldn't exist without the space you made for it.
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.