Getting Started
Mind Code is one agent harness across CLI, Web and Cloud agents: specs, steering and configuration travel with you.
Choose your surface
Pick the surface that fits your workflow. Your .mind/ configuration is shared across all of them.
What you can do
| I want to... | Use |
|---|---|
| Plan a feature with requirements, design, and tasks | Specs |
| Fix a bug with root cause analysis and regression prevention | Bugfix Specs |
| Chat and build iteratively without a plan | Chat in the CLI |
| Enforce project standards automatically | Steering |
| Automate actions on agent file changes, tool use, or task completion | Hooks |
| Connect external tools and APIs | MCP |
| Control what the agent can access | Permissions |
| Create specialised agents for specific workflows | Custom agents |
| Extend the agent with reusable instruction packages | Skills |
| Add tools with built-in knowledge that activate on demand | Agent Plugins |
| Delegate parallel tasks to focused sub-agents | Sub-agents |
| Undo agent changes or fork a conversation | Save and restore |
| Keep secrets and sensitive files away from the agent | mindignore |
| Keep long sessions productive within context limits | Context management |
Get started
One agent, every surface
Every Mind surface is a front end to the same unified agent harness. Your steering files, permissions, hooks, MCP servers, and custom agents work identically whether you're in the IDE, CLI, or Web — start a spec in the IDE, continue it from the CLI, hand off implementation to the Web agent, and everything stays in sync through .mind/.
Each surface adds its own way of working on top: the IDE brings editor integration, the CLI brings terminal-native and headless workflows, and the Web brings zero-setup sandboxed sessions.