# Engram

> Use this tool when you need to implement persistent memory for AI agents with controlled forgetting and efficient knowledge retrieval. Engram solves the problem of retaining and retrieving information over time, handling engineering state tracking and semantic graph queries. It takes in AI agent data and outputs relevant information, ideal for use cases requiring local, cloud-independent, and reliable memory management.

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

## Description

Persistent memory for AI agents with Ebbinghaus forgetting curve, semantic graph retrieval, and
engineering state tracking. Local-first, DuckDB, zero cloud dependency.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-13

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gh3r3jwjbm)
- **Repository:** <https://github.com/hugfeature/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": "hugfeature-engram"
    }
  }
}
```

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