# engram

> engram — lightmaze-engram. Use this tool when you need to revive and interact with past agent sessions, leveraging local-first and persistent participants to streamline collaboration and version control through git integration. It solves problems of session management and knowledge retention, enabling seamless recall of previous interactions. Ideal for use cases requiring attributed and bounded participant management, such as iterative project development and MCP-native applications.

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

## Description

Wake past agent sessions as named, bounded participants—local-first, attributed, persistent, and MCP-native.

## Trust

- **Trust score (0–1):** 0.71
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

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

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