Grok Build CLI vs Letta Code

Feature	Grok Build CLI	Letta Code
Tagline	Bring Grok into your terminal	The memory-first coding agent
Website	https://x.ai/cli	https://letta.com
Language	rust	typescript
Release Date	May 14, 2026	December 16, 2025
Last Updated	August 19, 2026	August 19, 2026
Provider Type	AI Lab	Independent
MCP Support	Yes	Yes
Multi-Agent Support	Yes	Yes
Git Integration	deep	basic
Multi-File Editing	Yes	Yes
Auto Test Running	Yes	Yes
Sandbox / Permissions	Yes	Yes
Image / Multimodal Input	Yes	Yes
Voice Mode	No	No
IDE Integration	None - Terminal only	None - Terminal only
Hooks / Extensions	Yes	Yes
Web Search	Yes	Yes
Local Model Support	Yes	Yes
Context Window	Model-dependent	Model-dependent
Terminal Bench	#9 · 20.3% ±3.1 (Terminal-Bench 4.0) 1	#44 · 59.1% ±2.4 (Terminal-Bench 2.0) 2
AA Coding Agent Index	47% · Grok 4.6 (xhigh)	-
Supported Models	SuperGrok Heavy, Grok 4.5, 4.20, Grok 4, Grok Build 0.1, custom models including OpenAI compatible models	Multi-provider with Claude, GPT, Gemini and self-hosted (BYOK).
Supported Subscriptions	SuperGrok X Premium	ChatGPT GitHub Copilot Claude Code OpenCode Go / Zen
Pricing Model	Subscription	Freemium
Free Tier	Yes	Yes
Price Range	$0 (3 Day Trial) / $30 monthly (SuperGrok) / $300 monthly (SuperGrok Heavy)	Free (BYOK) / $20-200/mo
Source Code Availability	Open Source (EULA)	Open Source (Apache-2.0)
Source Code	https://github.com/xai-org/grok-build	c
Development State	active	active

¹ Grok Build CLI tested with Grok 4.6 on Terminal-Bench 4.0.

² Letta Code tested with Claude Opus 4.5 on Terminal-Bench 2.0.