# engram

> engram — cognis-digital-engram. Use this tool when you need to implement a durable and long-term memory solution for AI agents, enabling them to store and retrieve information across sessions and interactions. It solves problems of knowledge retention and recall, allowing agents to learn from experiences and adapt over time. With interfaces to stdlib, SQLite, and MCP-native, it provides flexible input and output options for various applications and use cases.

Canonical page: https://skillsregistry.net/skills/cognis-digital-engram  
JSON: https://api.skillsregistry.net/v1/skills/cognis-digital-engram

## Description

Durable, model-agnostic long-term memory for AI agents — stdlib, SQLite, MCP-native

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/cognis-digital/engram)

## 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": "cognis-digital-engram"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-engram` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-engram/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