# MemForge

> Use this tool when you need to retain and retrieve engineering knowledge and project context across AI coding assistant sessions. MemForge solves the problem of lost project information and duplicated effort by storing and retrieving decisions, notes, and context using semantic search. It takes a PostgreSQL connection string and OpenAI-compatible embedding API as inputs and provides persistent team memory as output.

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

## Description

MemForge provides persistent team engineering memory for AI coding assistants using 47 MCP tools and pgvector-powered semantic search. It stores and retrieves engineering decisions, architecture notes, and project context across sessions using a self-hosted PostgreSQL database. The server requires a PostgreSQL connection string and an OpenAI-compatible embedding API.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/volsier-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": "volsier-memforge"
    }
  }
}
```

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