# engram

> engram — marccherggi-engram. Use this tool when you need to retain knowledge across sessions and recall relevant information to inform decision-making. Engram provides cross-session memory by compressing run trajectories into reusable conclusions and strategies, solving problems of knowledge retention and recall in complex tasks. It takes in run trajectories as input and outputs reusable conclusions and strategies, making it ideal for use cases where agents need to learn from past experiences and adapt to new situations.

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

## Description

Provides agents with cross-session memory by compressing run trajectories into reusable conclusions and strategies and recalling relevant priors via MCP.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xse6kz54dj)
- **Repository:** <https://github.com/MARCCHERGGI/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": "marccherggi-engram"
    }
  }
}
```

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