At a glance
A multi-provider terminal coding harness with repository tools, persistent project memory, automatic context compaction, primary and delegated agents, bounded workflow orchestration, headless and local web surfaces, MCP, skills, and Git-backed undo. It runs tools on the host: its permission policy and workflow runtime are controls, not an operating-system sandbox.
Good choice if
- Long-running repository work that benefits from persistent project memory and automatic context reconstruction
- Multi-provider or local-model workflows using primary agents, subagents, MCP servers, and reusable skills
- Headless and structured multi-agent workflows with bounded retries, parallel steps, and optional isolated Git worktrees
Check before choosing
- MiMo Code has no built-in process sandbox; the official security policy describes permissions as a user-experience control and recommends a container or virtual machine for isolation
- Most tool permissions default to allow, and the headless CLI can skip permission checks entirely, so unattended use needs an independently constrained runtime
- The workflow control script runs in QuickJS, but Bash and other tools still act on the host; worktrees separate repository files without containing processes, credentials, network access, or external side effects
See 2 more considerations
- Persistent memory and project instructions can influence later sessions, so durable context and generated workflow assets need review like other repository-controlled instructions
- Git-backed undo requires a Git repository, excludes ignored files and untracked files larger than 2 MiB, and cannot reverse shell, network, or other external side effects