# AHME

> Use this tool when you need to efficiently process and summarize large volumes of chat conversations into structured, easily readable formats. AHME solves the problem of information overload by automatically compressing conversations into key facts, decisions, and entities, and provides a persistent master memory file as output. It is ideal for use during system idle periods to avoid interfering with active AI workloads, taking in raw chat text as input and producing compressed JSON summaries.

Canonical page: https://skillsregistry.net/skills/dexopt-ahme  
JSON: https://api.skillsregistry.net/v1/skills/dexopt-ahme

## Description

AHME (Adaptive Hierarchical Memory Engine) is a local sidecar daemon that automatically processes and compresses chat conversations into structured summaries. It partitions incoming text into token-accurate chunks, waits for system idle periods to avoid interfering with active AI workloads, then uses local Ollama models to compress conversations into structured JSON containing key facts, decisions, open questions, and entities. Implements hierarchical merging to recursively combine summaries into higher-level memory blocks, maintaining a persistent master memory file readable by any AI tool.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/dexopt-ahme)
- **Repository:** <https://github.com/dexopt/ahme-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": "dexopt-ahme"
    }
  }
}
```

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