# Smriti

> Use this tool when you need to enhance the memory capabilities of LLM applications with persistent, graph-based memory recall. Smriti solves the problem of limited memory recall in LLMs by providing a scalable, cluster-aware retrieval system that combines cue extraction, graph traversal, and vector similarity. It takes in LLM application data and outputs human-like memory recall, making it ideal for use cases requiring advanced memory functionality.

Canonical page: https://skillsregistry.net/skills/gh-tejzpr-smriti  
JSON: https://api.skillsregistry.net/v1/skills/gh-tejzpr-smriti

## Description

Smriti provides persistent, graph-based memory for LLM applications built on LadybugDB embedded property graph database. It uses EcphoryRAG-inspired multi-stage retrieval combining cue extraction, graph traversal, vector similarity, and multi-hop association to deliver human-like memory recall. The system uses the Leiden algorithm for automatic community detection, enabling cluster-aware retrieval that scales beyond thousands of memories with automatic consolidation.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gh-tejzpr-smriti)
- **Repository:** <https://github.com/tejzpr/smriti-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gh-tejzpr-smriti"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gh-tejzpr-smriti` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gh-tejzpr-smriti/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt