# memforge

> memforge — memforgeai-memforge. Use this tool when you need to enhance the memory capabilities of AI agents, solving problems related to knowledge retention and recall. Memforge provides a single, unified Postgres-based memory layer, ideal for applications requiring efficient data storage and retrieval. It is particularly suited for use cases where MCP-native integration and high-performance benchmarking, such as LOCOMO, are essential.

Canonical page: https://skillsregistry.net/skills/memforgeai-memforge  
JSON: https://api.skillsregistry.net/v1/skills/memforgeai-memforge

## Description

The open-source memory layer for AI agents. MCP-native, single Postgres, #1 on LOCOMO benchmark.

## Trust

- **Trust score (0–1):** 0.75
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/MemForgeAI/memforge)

## 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": "memforgeai-memforge"
    }
  }
}
```

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