AHME is a **local sidecar daemon** that sits quietly beside your AI coding assistant. As you work, it compresses your conversation history into a
AHME is a local sidecar daemon that sits quietly beside your AI coding assistant. As you work, it compresses your conversation history into a dense Master
ollama pull qwen2:1.5b (or any 1–4B model)Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| ingest_context | text: string |
| get_master_memory | reset?: bool (default true) |
| clear_context | — |
{
"mcpServers": {
"ahme": {
"command": "python",
"args": [
"-m",
"ahme.mcp_server"
],
"env": {
"PYTHONPATH": "/absolute/path/to/ahme"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
ollama pull qwen2:1.5b (or any 1–4B model)| Variable | Description | Required |
|---|---|---|
| PYTHONPATH | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
MCP server for Enpass vaults: entries, passwords and TOTP/2FA codes, keychain-backed.
An MCP server that provides Unix command documentation directly within LLMs conversations.
An MCP (Model Context Protocol) server providing hybrid semantic search over code across a set of GitHub repositories that you list in `config.yaml`.
An MCP server that provides persistent memory and context management across sessions