# io.github.kael-bit/engram

> Use this tool when you need to implement a hierarchical memory system for AI agents, solving problems of information retention and retrieval in complex decision-making processes. It provides a three-layer architecture with buffer, working, and core memory components, featuring decay and promotion mechanisms to manage knowledge priority. Ideal for use cases requiring adaptive learning and knowledge management in dynamic environments.

Canonical page: https://skillsregistry.net/skills/io-github-kael-bit-engram  
JSON: https://api.skillsregistry.net/v1/skills/io-github-kael-bit-engram

## Description

Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.10.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-17

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.kael-bit%2Fengram)
- **Repository:** <https://github.com/kael-bit/engram-rs>

## 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": "io-github-kael-bit-engram"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-kael-bit-engram` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-kael-bit-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