# engram

> engram — blakestone-x-engram. Use this tool when you need to implement a robust memory system for AI agents, enabling them to store and recall information in a markdown-native format, with features like tiered memory and forgetting curves to mimic human-like memory consolidation. It solves problems related to knowledge retention and retrieval, allowing agents to learn and adapt over time. With git integration, it provides a version-controlled interface for inputting and outputting knowledge, making it ideal for applications requiring local-first, persistent memory.

Canonical page: https://skillsregistry.net/skills/blakestone-x-engram  
JSON: https://api.skillsregistry.net/v1/skills/blakestone-x-engram

## Description

Local-first, markdown-native memory for AI agents: tiered memory, an Ebbinghaus forgetting curve, consolidation, and an MCP server.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/blakestone-x/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": "blakestone-x-engram"
    }
  }
}
```

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