Codewhale vs. Muse Code

Feature	Codewhale	Muse Code

Tagline	Community-driven coding agent that runs a different model per role	Meta's coding agent for the terminal and CI, built on Muse Spark
Website	https://codewhale.net/	https://developer.meta.com/ai/products/muse-code/
Language	rust	rust
Release Date	January 19, 2026	August 5, 2026
Last Updated	September 4, 2026	September 4, 2026
Provider Type	Independent	AI Lab
MCP Support	Yes	Yes
Multi-Agent Support	Yes	Yes
Git Integration	deep	deep
Multi-File Editing	Yes	Yes
Auto Test Running	Yes	No
Sandbox / Permissions	Yes	Yes
Image / Multimodal Input	Yes	Yes
Voice Mode	Yes	Yes
IDE Integration	Editors via ACP (registry submission pending)	None - terminal only
Hooks / Extensions	Yes	Yes
Web Search	Yes	No
Local Model Support	Yes	No
Context Window	Model-dependent	1M tokens
Supported Models	30+ providers: DeepSeek, Claude, GPT, Kimi, GLM, Qwen, Grok, Mistral, Xiaomi MiMo, Alibaba Model Studio, SiliconFlow, OpenCode Zen, Hugging Face; local via vLLM, SGLang, Ollama	Muse Spark 1.2, Muse Spark 1.1
Supported Subscriptions	ChatGPT SuperGrok	—
Pricing Model	Free, BYOK	Usage Based
Free Tier	Yes	No
Price Range	Free (BYOK)	Usage-based (from $0.10/M tokens)
Source Code Availability	Open Source (MIT)	Proprietary Software
Source Code	https://github.com/Hmbown/CodeWhale	N/A
Development State	active	active