>> mq-agent
Most AI tooling puts the model at the center. You describe a task, the model decides how to fulfill it, and you watch what happens. mq-agent starts from the opposite assumption: the model is one component in a pipeline, not the pipeline itself.
The agent connects to mq-mcp — a local MCP server that exposes tools
for repository analysis, architecture decisions, code review, and diagnostics.
When you run mq-agent review diff, the agent calls the right tool,
passes the result back, and renders it.
The model routes and formats. The tools do the work.
The command surface was a deliberate constraint.
score, audit, review, doctor:
each command maps to a specific tool call.
There is no open-ended prompt interface because there does not need to be.
A well-defined task needs a well-defined command, not a general-purpose chat window.
The integration with mqlaunch follows the same logic. The menu delegates to the agent, the agent calls mq-mcp, and the result surfaces in the terminal. Nothing leaves the machine unless explicitly asked. Local infrastructure, local model, local context.
Architecture memory is stored through mq-mcp as a list of decisions — not a diagram, not a document, but a queryable set of records. When you run a review, the agent pulls the relevant decisions and displays them alongside the findings. Context that was previously implicit becomes part of the output.
The interesting thing about building an agent is discovering how little the model actually needs to do. The hard work is the tool design, the routing, and the contracts. Get those right and the model becomes almost invisible. That is the point.