At a glance
SpaceXAI's open-source terminal coding agent with TUI, headless and ACP surfaces, custom models, MCP, plugins, default-on subagents, plan review, conversation rewind, permissions, and optional OS-level sandbox profiles.
Good choice if
- Plan-review-execute workflows with explicit diffs and permission controls
- Terminal, CI, or ACP integrations that need structured output and resumable sessions
- Extensible setups using MCP, plugins, subagents, custom models, and worktrees
Check before choosing
- The OS sandbox is off by default; strict/read-only child-network blocking is Linux-only, in-process model and web traffic remains outside that rule, and sensitive paths such as ~/.ssh require explicit deny configuration
- Worktrees isolate checkouts rather than processes, while always-approve can skip tool prompts unless enterprise requirements explicitly disable bypass mode
- Cross-session memory is optional and off by default; /rewind now truncates conversation without restoring files, while snapshot-code restoration for a remote resume is opt-in and requires --worktree --restore-code; neither path can undo external side effects
See 3 more considerations
- Browser review is supplied through plugins or MCP rather than a core browser tool, and web fetch is separately gated
- The public repository is a periodic monorepo sync, has no public CI workflow, does not accept external contributions, and may not identify the exact source revision used for a shipped binary
- The statement that Grok 4.5 powers the product is model branding, not evidence of harness quality; no complete independent product benchmark is imported