convez.ai
MCP Server
yugandhar-maram

agrasandhany

yugandhar-maram/agrasandhany

Ver no GitHub
InicialPluginScore · de 0 a 100

turn local notes into long-term memory for AI agents

Instalação

$npx convez-ai yugandhar-maram/agrasandhany

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
5
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

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.md is tagged projects/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

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

License

MIT


Dedicated to my wife — for the evenings, the weekends, and the patience. This wouldn't exist without the space you made for it.

Ver o original no GitHub

Relacionados