Claude Code vs Letta Code

Feature	Claude Code	Letta Code
Tagline	An agentic coding tool that lives in your terminal	The memory-first coding agent
Website	https://claude.ai/code	https://letta.com
Language	typescript	typescript
Release Date	February 22, 2025	December 16, 2025
Last Updated	September 4, 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	Yes	No
IDE Integration	VS Code, JetBrains	None - Terminal only
Hooks / Extensions	Yes	Yes
Web Search	Yes	Yes
Local Model Support	Yes	Yes
Context Window	1M tokens	Model-dependent
Terminal Bench	#2 · 57.9% ±3.8 (Terminal-Bench 4.0) 1	#44 · 59.1% ±2.4 (Terminal-Bench 2.0) 2
AA Coding Agent Index	70% · Fable 5.1 (max, with fallback)	-
Supported Models	Claude Fable 5 / Mythos 5 (Restricted Availability), Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5	Multi-provider with Claude, GPT, Gemini and self-hosted (BYOK).
Supported Subscriptions	Claude Code	ChatGPT GitHub Copilot Claude Code OpenCode Go / Zen
Pricing Model	Subscription	Freemium
Free Tier	No	Yes
Price Range	$17-200/mo	Free (BYOK) / $20-200/mo
Source Code Availability	Proprietary Software	Open Source (Apache-2.0)
Source Code	https://github.com/anthropics/claude-code	c
Development State	active	active

¹ Claude Code tested with Fable 5.1 on Terminal-Bench 4.0.

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