ingest_contextLABSCO SUMMARY
Summarising costs nothing when the summariser is local.
Context compression is normally paid for twice — once in tokens to produce the summary, once in latency while you wait for it. Running a 1–4B model on your own machine during idle CPU removes both, and it means the conversation history never leaves the laptop. The design decision to notice is that reading the memory also resets it: the call hands back the summary and re-seeds from it, so this is a checkpoint mechanism rather than an append-only archive.
What it is
A local daemon that sits beside an AI coding assistant and keeps a running summary of what has happened. Conversation goes in, a queue holds it, and when the CPU is idle a small local model compresses it — recursively merging into a single Master Memory Block. Nothing leaves the machine and nothing is billed.
What you get
- Three tools, and that is the whole surface —
ingest_context,get_master_memory,clear_context - A persistent SQLite queue in front of the compressor, so ingested context survives restarts instead of being lost with the process
- Compression that waits for idle CPU rather than competing with your work, producing structured JSON that merges recursively into one block
- A context-window replacement pattern on read:
get_master_memoryreturns the compressed summary, clears the old data, and re-seeds the engine with that summary — so the next conversation starts dense rather than empty - The same memory written to
.ahme_memory.mdon disk, which means tools that read files but do not speak MCP can still use it
Requirements
No account and no key — the model runs locally. Python 3.11+, Ollama running on the machine, and a small model pulled: the README suggests ollama pull qwen2:1.5b, and any 1–4B model works. Install from a clone with pip install -e ., copy config.example.toml to config.toml, and set the model line under the ollama section — the README states that is the only line you need to change. The server launches as python -m ahme.mcp_server with PYTHONPATH pointed at the checkout, and a ready-made .mcp.json ships in the repository root.
Setup effort
Build from source — ollama pull qwen2:1.5b
USE CASES
01
Carrying a long refactor across several sessions
Ingest as you go, then open the next session by pulling the memory block, so the decisions already made arrive with the first message.
02
Keeping project context out of the cloud
Run the compression on a local Ollama model so conversation history is summarised on the machine it happened on.
03
Sharing memory with a tool that does not speak MCP
Point the other tool at the Markdown file the engine writes, and let it read the same compressed block.
04
Starting clean when the thread has gone stale
Clear the accumulated context deliberately instead of letting an outdated summary keep seeding new sessions.
3 tools
Listed in project docs. Your client may show a different list.
get_master_memoryclear_contextBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- python on PATH
- Python 3.11+
Where it runs
All 6 documented clients run the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
ollama pull qwen2:1.5b
git clone https://github.com/DexopT/AHME-MCP.git
cd AHME-MCP
cp config.example.toml config.toml
pip install -e .MCP Clients
Claude Code, Kilo Code, Cursor, Windsurf, Cline, Antigravity
JSON
{
"mcpServers": {
"ahme": {
"command": "python",
"args": [
"-m",
"ahme.mcp_server"
],
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_AHME_MCP>"
}
}
}
}
