Command Code
@CommandCodeAI
Meet the coding agent built for open models. Command Code. We do tool repairs, /design, #1# on leaderboards, and the world's best $10 GOAT plan w/ $70 usage.
2 Following 24.5K Followers
Extending $60 usage on DeepSeek V4.1 Flash another 8 days. 🐐
DeepSeek V4.1 Flash is live in Command Code.
6x usage on $10/mo GOAT for a week.
$60 usage. 154K requests. 7.8B tokens.
GOAT plan is the best AI coding plan.
Available in all plans and API.
🐐
I owe @CommandCodeAI a shoutout.
I’ve been posting a lot about how good DeepSeek V4.1 Flash is, but I’d mostly been using it through Hermes with Command Code as a provider.
I finally tried Command Code’s own harness.
The difference is ridiculous.
Same V4.1 Flash, but responses feel dramatically faster and the whole experience is much more immediate.
Hermes is great for long-running autonomous work, but Command Code feels so much better for interactive coding and quick back-and-forth.
The desktop app seems great so far too.
I seriously underestimated how much the harness changes the experience.
Show more
Command Code is fastest DeepSeek inference in the world.
Better
Faster
Cheaper
All the work we put into tool repairs have and harness + inference engineering is paying dividends now.
Our mission is to be inference-native.
Let's go, GOAT 🐐
Show more
GLM-5.3 FlashX is now live in Command Code.
· High speed variant of GLM-5.3 Flash
· ~200 TPS with 1M context window
· Multimodal (text, image, video)
Available across all plans and API.
Qwen 3.8 Omni Flash is now live in Command Code.
Available across all plans and API.
Command Code outperformed every other harness on open models like DeepSeek in Composio's bench. 🐐
🔹 Most accurate: Solved 18/30 tasks
🔹 Fastest avg time per tasks: 375s
Beating even DeepSeek's own harness.
Show more
I’m trying out the @CommandCodeAI macOS app released yesterday. It didn't have a "Computer Use" feature initially, so I asked it to use an open-source tool to handle that functionality (DeepSeek 4.1 Flash). And it created an MCP server for UI-TARS, wrote its own computer-use capability, and is now working flawlessly. Although it’s a bit slower compared to Codex and Claude, but man it is incredibly cheap.
Here is a screenshot showing it playing XOX on Google:
Show more
Stop copy-pasting errors. IDE diagnostics are quite strong.
Open Command Code. Select your code. Type fix this
Command Code is one of the most token efficient top tier harnesses - leading accuracy, cost, and speed for both open and closed frontier models!!
Introducing Command Code Desktop App! ⌘
Available today in beta for Mac, Linux, & Windows.
Building the most powerful agentic app, starting with code. Multiple agents, files, Git, terminal, browser previews, plans, and instant edits with /design.
This is just the beginning.
Show more
Introducing Command Code Desktop App! ⌘
Available today in beta for Mac, Linux, & Windows.
Building the most powerful agentic app, starting with code. Multiple agents, files, Git, terminal, browser previews, plans, and instant edits with /design.
This is just the beginning.
Show more
Super excited for the launch tomorrow.
Mods are more powerful than plugins.
Command Code can build mods and modify any behavior from programmatic hooks to a completely different inference provider.
We bet you haven’t experienced something as powerful before.
Build a mod now and make Command Code do anything you want.
Show more
Mods are more powerful than plugins.
Command Code can build mods and modify any behavior from programmatic hooks to a completely different inference provider.
We bet you haven’t experienced something as powerful before.
Build a mod now and make Command Code do anything you want.
Show more
something is not normal with @CommandCodeAI
I refactored our entire docs and only used 14% of the monthly limits
you're insane @MrAhmadAwais
Last week these models went live in Command Code.
DeepSeek V4.1 Flash
Muse Spark 1.3 (with max reasoning)
Ling 3.0 Flash Sante (free model)
🐐
DeepSeek V4.1 Flash is live in Command Code.
6x usage on $10/mo GOAT for a week.
$60 usage. 154K requests. 7.8B tokens.
GOAT plan is the best AI coding plan.
Available in all plans and API.
🐐
Ling 3.0 Flash Sante is now free in Command Code.
5.1B active params. all subs. all plans
npm i -g command-code@latest
🐐
Muse Spark 1.3 Max is live in Command Code.
New reasoning effort param for harder problems and frontier performance.
Run /model, select Muse Spark 1.3
Then choose max for reasoning effort
Next week. Hello, Desktop.
