Ahmad Awais

closed models get better when one lab decides to ship. open models get better every time anyone touches them. a quant here, a fine-tune there, a new inference trick from someone's weekend project. one roadmap vs a million. i know which one i'm betting on.

97.8% of US households don’t pay for AI. (a16z) AI is priced for SF. this needs to change! At Command Code, we’re building frontier intelligence for the other 97.8%. We started with developers. Next up is work, education, and daily life. 50K+ paying customers already.

a $200/mo AI plan is a rounding error in SF. it's a month's rent for a lot of developers around the world. open models are how the next million developers get to build. that's why we're obsessed with cheap tokens at Command Code.

i've watched this movie before. linux vs unix. wordpress vs every cms with a sales team. node vs the enterprise java stack. open didn't win because it was better on day one. it won because everyone could make it better. open models are on the same path. same ending.

a closed model can be deprecated on a tuesday. new pricing, new rate limits, new "safety" tune that breaks your prompts. open weights you download today still run exactly the same in 10 years. build on what can't be taken away from you.

Today we're launching Agr, an open decision model by Command Code. · Agr (31B) and Agr-flash (360M) · 58.15 on Decision Index 0.2.1 · Focus: tool calls & routing · TypeSafe SDK support Agr is best-in-class on coding agent tool calls and routing. Live on Hugging Face today.

YeahSend state as text or JSON with typed questions. Agr skips text generation and returns typed values with a probability for each option. With Agr, you can own your decision routing stack, deploy on prem with Agr (31B params), or local AI on your device with Agr-flash (360M params).

huggingface.coCommandCode/agr · Hugging FaceWe’re on a journey to advance and democratize artificial intelligence through open source and open science.

Agr model family is available on Hugging Face and GitHub. We’ll work closely with the open-source community on inference support and explore more deployment options. Planning a large scale deployment? Let’s talk. huggingface.co/CommandCode...

my code is on Mars because someone open sourced their framework and let a random 20-something kid contribute to it. you give first, and it ends up in places you never imagined. open models are that, for intelligence. 🚀

open source is changing though. a lot of maintainers are shutting down PRs and rethinking all of it. bumpy ride right now, but i'm sure the open community figures this out. we're working on how to do open source well too. more open source landing next week.

two types of developers in 2026 1. ai is taking my job 2. ai is doing my job and i'm shipping 3 more be type 2. wbu?

everyone's benchmarking new models on 3D games again. we did flappy bench last month so i'm not innocent lol but the bench i actually care about is tokens burned per real fix in a real repo. that's why we built TEF bench.

commandcode.aiThe Shell Tool | Command CodeThe token efficiency frontier: we priced 23 shell-tool capabilities by the tokens each one saves, benchmarked ten coding agent harnesses from source at pinned commits, and our curve is the frontier at every step. Background execution, wake-ups instead of polling, cursor reads, honest exit codes, and kill by port.

full TEF bench here: commandcode.ai/docs/harnes...

labs cut prices 50%. open models did that. fwiw we're one of the largest buyers of open model tokens on the planet. every cut makes the GOAT plan even more unfair. 🐐

Excited to announce Remote Control /rc in Command Code You can now use Command Code on your phone, tablet, or even browser starting with Telegram and Discord. · Run /rc to open your session in Telegram or Discord · Work from your phone and get live responses 🐐

commandcode.aiRemote control | Command CodeRun /rc and your session shows up in Telegram or Discord, so you can keep working from your phone.

commandcode.ai/docs/rc

github.comGitHub - CommandCodeAI/cmd-mod-jev-nudge: Command Code mod: nudges the agent to keep going when it stops with work left, judged by JevCommand Code mod: nudges the agent to keep going when it stops with work left, judged by Jev - CommandCodeAI/cmd-mod-jev-nudge

22 Sept

Launching Jev on Command Code for free today. Jev x Command Code is super interesting. You can only use Jev in headless mode or Provider API. Also open sourced a mod "cmd-mod-jev-nudge" Use Jev for free to keep your agent running as long as the there's more work to do. github.com/CommandCode...

16 Sept

Introducing Command Code Desktop App ⌘ Available today in beta for Mac, Linux, & Windows. We're building the most powerful agentic app, and code is where we start. Run multiple agents at once, work with files, Git, and the terminal, preview in the browser, make plans, & make instant edits /design.

12 Sept

DeepSeek V4.1 Flash, first 24 hours of launch, broke all records!! Command Code served 3.1 TRILLION paid tokens. More than OpenRouter, OpenCode etc, or anyone else in the world. Sustained 230-300 TPS. Better, faster, cheaper!! 🐐

26 Aug

MiniMax M3 and M2.7 are now free in Command Code. next 10 days. all subscribers. all plans 🐐

Introducing, the best open models plan: GOAT 🐐 Command Code GOAT plan is the best low-cost coding plan on the market today. - $10/mo to get $70 credits. 7x what you pay - 30+ open weight & closed models $1 Go was a tease I know. GOAT lasts full month. Subscribe — be a GOAT.

Yes, we're so confident in our v1 Command Code CLI that we now have no issue offering an API. We know you'll return for the best harness engineering, top notch harness tool, free tool repairs that save your sessions, and ~98.78% industry leading cache hit ratio.

We've crossed 30K paid customers, 100K+ developers, and 10 Trillion token scale. It's our 3rd month. Desktop app is in alpha, and two new products coming.

With the v1 release, which is a full rewrite of this 6-year-old codebase, it's now arguably one of the best, most mature coding agent harnesses. Check out the new Mods API - you can build anything you can imagine. We can't wait to see what you build with Command Code.

We're also open sourcing Command Code later this month. It's finally time. We are almost ready. 86% review done. Does it have API access?

From getting DeepSeek to beat Opus, to building infra with leading ~98% cache hit rates, to fixing AI slop with the built-in /design skill - Command Code has made its way to the top of the open model coding world, everywhere.

The GOAT plan is the next step in that journey: open models, accessible to everyone. Open models are already beating frontier closed models at coding. How rich is this moment if you think of it.

The GOAT plan fixes that - it's the best value in the coding market today, with enough credits to do something meaningful with open models.

Coding with open models comes with hard problems - cost, reliability, safety, and the sheer complexity of running them well. We set out to solve all of it, so you can pick an open model and just code.

While almost every other coding agent was built to serve closed models, we built Command Code to be the best coding agent harness for open models.

commandcode.aiGOAT Plan | Command CodeThe best low-cost coding plan: Command Code GOAT at $10/month. Unlimited coding on 30+ top open source and closed source models - pay $10, get $70 of credits, a 7x multiplier. With deals, usage stretches beyond $100.

We started with the $1 Go plan. The sheer audacity of that plan was a hit, but it was also a bit of a tease: a great way to get started, not enough usage to last the month.

Get started → commandcode.ai/docs/plans/... Why create the GOAT plan? At Command Code, we're incessantly curious about 1) open models, 2) how to get the best value out of them, and 3) how to make that value accessible to everyone. The GOAT plan is our answer to all three.

3 Aug

Qwen 3.8 Max is now live in Command Code Go. … and it's going open weight!! most importantly, next week open-weights of Qwen3.8-Max and Qwen3.8-27B will be released! 🔹 2.4T params MoE flagship 🔹 Input: $2 Output: $6 🔹 Cache: $0.25 / M tokens 3.8 is 20% cheaper than 3.7

20 July

Command Code is the most used coding agent on open router overtaking Claude Code, Cursor, OpenClaw, Kilo, Cline, etc in just two months. Command Code is purpose built for open models. Devs using it to get the most out of open models, save the most money, get the best caching & tool call repairs

18 July

update: today Command Code overtook Claude Code on OpenRouter. devs are picking the harness built for open models over monkey-patching proxy hacks into claude code. it has sub par perf & wastes your time/money with open models as it's only meant for claude models. x.com/MrAhmadAwai...

18 July

use a better harness to get the best open models performance, and to save time and money. read this why ↓ x.com/MrAhmadAwai...

12 June

Got interviewed by Business Insider on how enterprise are switching to open models. With Command Code gaining over 10K paying customers in 30 days. Demand for cheaper yet intelligent open models is growing fast, we've made open models outperform closed, most of my research on this is public.