# A-Mem

> Use this tool when you need to enhance AI agents with self-evolving memory capabilities, solving problems of knowledge retention and retrieval in dynamic environments. A-Mem takes in new knowledge inputs and outputs updated connections between semantically similar memories, leveraging a dual-mode search interface for efficient retrieval. Ideal for use cases requiring adaptive learning and knowledge graph updates, supporting multiple LLM backends for flexible integration.

Canonical page: https://skillsregistry.net/skills/diaaaj-a-mem  
JSON: https://api.skillsregistry.net/v1/skills/diaaaj-a-mem

## Description

A-Mem provides self-evolving memory capabilities for AI agents through a dynamic knowledge graph. When new knowledge is added, the system identifies semantically similar existing memories and strengthens or updates connections between them. Features dual-mode search combining semantic vector similarity with graph traversal, and token-efficient retrieval using lightweight metadata summaries. Supports multiple LLM backends including OpenAI, Ollama, SGLang, and OpenRouter.

## Trust

- **Trust score (0–1):** 0.76
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/diaaaj-a-mem)
- **Repository:** <https://github.com/diaaaj/a-mem-mcp>

## 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": "diaaaj-a-mem"
    }
  }
}
```

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