MindMux Overview
MindMux is a local-first AI workbench built around a project brain. It gives product and engineering teams one place to discuss ideas, distill stable knowledge, and dispatch execution without losing the reasoning that led there.
Unlike a general chat client, MindMux treats conversation as an interface, not the final output. The durable asset is the brain/: structured Markdown documents, knowledge pages, and execution context that remain usable across sessions, runtimes, and agents.
Product Thesis
MindMux exists for teams that already know chat alone is not enough. Good discussions happen in chat, but durable projects need:
- stable project memory
- explicit decisions and rationale
- reusable context across sessions
- a clean handoff from thinking to execution
MindMux is designed around a simple loop:
- Discuss
- Distill
- Dispatch
What Makes It Different
A project brain, not a transcript archive
MindMux keeps durable context in a local brain/ directory instead of trapping it inside a single vendor’s chat history. The brain contains:
- six project-level root docs
- structured knowledge pages with lifecycle status
Sessions that can resume, fork, and open new topics
Sessions are first-class objects. They can be resumed, forked from a specific point, or opened as separate new-topic sessions suggested by the agent while staying connected to the same project brain.
Runtime-portable knowledge
MindMux separates the knowledge layer from the execution layer. Claude Code, Codex, and other runtimes can work against the same brain without forcing users to rebuild context every time the runtime changes.
Lightweight execution handoff
MindMux can turn a settled discussion into a task, attach the relevant brain context, and dispatch it outward. The task system is intentionally lightweight: it is an execution bridge, not a project management suite.
Core Building Blocks
Project
The top-level unit users work in. Public-facing language should usually say “project”, even though parts of the implementation use the term “workspace”.
Brain
The durable knowledge layer stored as files. This is the long-lived memory of the project.
Session
A discussion thread with its own runtime, expert, origin relationship, and message history.
Expert
The in-app discussion role that shapes how a session reasons and responds.
Runtime and profile
The execution pair that determines which model system runs the conversation or task.
Task
The outbound execution unit used when discussion becomes actionable work.
What This Documentation Covers
- Getting Started covers installation, project setup, and the first meaningful workflow.
- Core Concepts explains the data model and operating model.
- Workflows shows how teams actually use MindMux day to day.
- Architecture explains the desktop app, runtime boundary, MCP integration, and storage model.
- Reference documents the concrete file structures and lifecycle rules.