ask_localLABSCO SUMMARY
Frontier reasoning spent only where it is needed.
The routine work an agent gets handed — a summary, an extraction, a commit message, a first look at a diff — runs on your own hardware with a prompt already tuned for it, which keeps both the budget and the paid model's context for the parts that need them.
What it is
A set of purpose-built tools that route work to your local Ollama instance. Each ships with a baked-in system prompt and a description written for the calling agent, so the handoff happens at the right moment and comes back tuned rather than raw.
What you get
- A log, a document or a transcript summarised locally, with a summariser prompt already in place
- A first-pass code review from the local model, behind a reviewer prompt
- A commit message drafted from the change
- Structured values pulled out of text — every URL in a file, and the like — behind an extractor prompt
- A plain question or an ongoing chat sent to the local model when the answer does not need frontier reasoning
Requirements
Ollama running locally with at least one model pulled — the project's example is qwen2.5-coder:14b. Python 3.11+, or uvx which manages it for you. Two dependencies, mcp and httpx, and no telemetry. Everything runs on your machine, so the cost is your GPU rather than tokens.
Setup effort
One command — uvx ollama-handoff
USE CASES
01
Summarising a long log without spending on it
The summariser prompt is already in place, so the handoff is one call and the result comes back shaped.
02
Getting a first look at a diff
A local reviewer pass catches the obvious things before the expensive model reads it.
03
Writing the commit message
Drafted locally from the change, which is a task that almost never needs a frontier model.
04
Pulling every URL, id or address out of a file
Extraction behind an extractor prompt, rather than a general model asked to be careful.
05
Asking something that does not warrant the big model
A one-shot question or a running conversation, answered on your own GPU.
8 tools
Listed in project docs. Your client may show a different list.
chat_localsummarize_localcode_review_localdraft_commit_message_localextract_locallist_modelsserver_infoBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
- uvx on PATH
- Python 3.11+
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx ollama-handoffMCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add ollama-handoff -- uvx ollama-handoffClaude Desktop, Cursor
JSON
{
"mcpServers": {
"ollama-handoff": {
"command": "uvx",
"args": [
"ollama-handoff"
],
"env": {
"OLLAMA_DEFAULT_MODEL": "qwen2.5-coder:14b"
}
}
}
}
