# agent-mem

> agent-mem — junknet-agent-mem. Use this tool when you need to efficiently manage memory for AI agents, such as Claude or Cursor, and require features like active file watching and auto-distillation via Large Language Models (LLM). It solves problems related to memory optimization, version control, and data consistency, providing a 'Single Source of Truth' for AI agent data. With native MCP support and git capabilities, agent-mem streamlines memory management, taking inputs from files and outputs optimized memory configurations.

Canonical page: https://skillsregistry.net/skills/junknet-agent-mem  
JSON: https://api.skillsregistry.net/v1/skills/junknet-agent-mem

## Description

High-performance, pure Go memory middleware for AI Agents (Claude/Cursor). Features active file watching, auto-distillation via LLM, and 'Single Source of Truth' versioning. Native MCP support.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/junknet/agent-mem)

## 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": "junknet-agent-mem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/junknet-agent-mem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/junknet-agent-mem/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