# agentsmd-memory

> Use this tool when you need to manage project memory in AGENTS.md, enabling agents to record and remove durable facts. It solves problems related to knowledge retention and updating, allowing for efficient information management. The tool accepts save and forget commands as inputs and outputs updated project memory, making it ideal for use cases requiring dynamic fact management.

Canonical page: https://skillsregistry.net/skills/jryom-agentsmd-memory  
JSON: https://api.skillsregistry.net/v1/skills/jryom-agentsmd-memory

## Description

MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/barbons7yo)
- **Repository:** <https://github.com/jryom/agentsmd-memory>

## 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": "jryom-agentsmd-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jryom-agentsmd-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jryom-agentsmd-memory/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