Command Code

We've raised $5M to launch the first coding agent that can continuously learn your coding taste. Introducing Command Code. $ npm i -g command-code Code 10x faster. Review 2x quicker. Bugs 5x slashed. Taste >>>> AI Slop.

Coding agents shine when used for reasoning, not just generation. Try this Active Comparison workflow: 1. Draft first: Ship a rough solution, even if it's messy. 2. Challenge the agent: Ask it why it would refactor specific parts. 3. Diff the logic: Compare its version with yours line-by-line. 4. Audit the tradeoffs: Ask it to justify readability vs. performance. You aren't just getting an answer; you’re building taste. AI speeds up the feedback loop, but the real learning happens in the gap between your version and its.

Coding agents are reshaping how we build software. Here is a simple way to use them well: 1. Start with a clear goal 2. Give context and constraints 3. Review outputs and refine The secret is taste. Guide the agent with good judgment and it will amplify your skills.

AI use case: Log analysis AI can scan logs and instantly surface errors, anomalies, and root causes. It helps you debug faster and resolve issues before they escalate.

AI Terminology #20: Distillation ↳ A training technique where a smaller “student” model learns to replicate the behavior of a larger “teacher” model, preserving performance while reducing size and cost. x.com/CommandCodeAI/…

@MaedahBatool Woohoo! 🥳🥳🥳

New role: Product Lead at @CommandCodeAI 🥳 After building developer experience at Vercel (Next.js) and then Sourcegraph, I'm going all in on what comes next. Excited to announce that I've joined Command Code to build and shape the next frontier of developer experience. I'll be working across Product and GTM to help developers take command of their code. Command Code is the first frontier coding agent that both builds software and continuously learns your coding taste via `taste-1`, our meta neuro-symbolic AI model. We're hiring in SF and globally. Come work with us on building the future of agentic engineering. Let's goooo!!

AI is the new operating system for builders. Research in minutes. Code in hours. Ideas turned into products faster than ever. The people who treat AI like a daily tool will move 10x faster than those who do not. Are you using it every day?

AI coding agents are moving beyond autocomplete. ↳ Break tasks into executable steps ↳ Write code, run it, debug failures ↳ Improve outputs through execution loops Code generation backed by runtime feedback. Follow for more insights on AI and coding agents.

@MrAsharIrfan noice ship!!!

Introducing `tikr` A Pomodoro & countdown timer for the terminal. Built with Command Code. No app switching. No browser tabs. No distractions. $ 𝚗𝚙𝚡 𝚝𝚒𝚔𝚛-𝚌𝚕𝚒

Star it ↳ github.com/ahmadawais/cha… | ↳ Built with @CommandCodeAI [CommandCode.ai] | npm i -g command-code | | # how? | $ cd my-cli-project | | # pull my coding taste ↳ $ npx taste pull ahmadwais/cli | ↳ $ cmd "build me a CLI with Ahmad's taste that …"

I got Amjad @amasad to invest in @CommandCodeAI back when Replit was a $2M ARR company, before the $9B decacorn it is today. I've been fortunate and intentional to have great founders on our cap table. Followed Amjad's work for a long time. He's one of those founders who just quietly, consistently executes at a high level. Few people sustain that kind of output over 10+ years. It's rare and I have a lot of respect for it.

People think coding agents only work for small tasks. “Agents can’t handle complex projects.” Coding agents can break big problems into steps, execute them, and iterate — helping you move large projects forward faster. How are you using coding agents today?

Have you tried commandcode.ai yet? Give it a try!

AI use case: Code search AI can instantly find functions, files, or patterns across huge codebases. It helps you jump straight to the code that matters. How do you search through your codebase?

Introducing mmmodels 𝌭 𝚖𝚖𝚖𝚘𝚍𝚎𝚕𝚜 is a CLI for browsing, filtering, and exploring AI models from hundreds of providers. Built for both humans and agents. $ 𝚗𝚙𝚡 𝚖𝚖𝚖𝚘𝚍𝚎𝚕𝚜 I wanted one terminal-native place to answer questions like: - what models exist (fuzzy search) - who ships them at what price - how much context they have - what they cost (esp caching) - which ones support tools, reasoning, files, or structured output The data is all there. The workflow as a CLI was missing. Cognitive load of issues like: Name drifts. IDs collide across providers. Pricing and capability metadata changes constantly. The browser/tab workflow is too slow if you do this often (as someone building a frontier coding agent). Again built with Command Code, with my CLI taste. What it does well: - no-arg interactive TUI for browsing `mmmodels` all you need - fuzzy search across model IDs, model names, and provider names - filtering by provider, capabilities, and status - explicit sorting and limiting with `--sort` and `--limit` - agent-friendly output with `--fields`, `--ids-only`, `--ndjson`, and `--json` - width-aware terminal tables that fail cleanly instead of overflowing - `--plain` mode for scripts, CI, and remote boxes - local disk cache with offline-friendly fallback behavior A few examples: $ mmmodels claude $ mmmodels list --provider anthropic --table $ mmmodels search gpt --provider openai --json $ mmmodels search claude --fields id,provider_id,limit.context,cost.input One subtle feature I like: provider-aware ranking. If the same model family appears from multiple providers, search prefers the default source for that family instead of returning an arbitrary duplicate first. Under the hood the search is custom-scored. PRs welcome. Queries are tokenized, normalized, version-aware, and AND-matched across candidates. Version tokens like `4.6` are handled carefully so they do not accidentally match `4.5`. Caching is simple on purpose: - in-process cache - disk cache in tmp - network fetch from source - do --sync or -s with any command to fetch live Normal mode goes memory -> disk -> network. If the fetch fails, it falls back to disk cache instead of hard-failing. Tables are width-aware. Each column has min/max widths and alignment. The renderer fits the table to the current terminal width, and if the requested columns still do not fit, it errors instead of wrapping into unreadable soup. `--plain` actually means plain: - no banner - no color - no spinner - booleans rendered as `yes/no` - ASCII connectors instead of box-drawing glyphs No dashboards. No browser spelunking. Big win. Need I say more. Just: $ npx mmmodels Or install it globally: $ npm i -g mmmodels If you work with models a lot and prefer terminals over tabs, try it. ⌘ Built with Command Code.

AI Terminology #19: Quantization ↳ A technique that reduces the precision of a model’s numbers (e.g., from 32-bit to 8-bit) to make it smaller, faster, and more efficient to run. x.com/CommandCodeAI/…

AI is the new unfair advantage. The same person with AI can research faster, write faster, code faster, and ship faster. The gap will not be small. It will compound daily. People who adopt early will look unstoppable later. Are you building with AI yet?

built with @CommandCodeAI

Super excited to welcome you Vipul. ⌘ LFG! Too many “vibe coding tools” miss the mark for top full-stack devs. Great engineering needs taste, and that’s exactly what we’re bringing to agentic coding with taste.

AI coding agents are becoming production-grade development partners. They don’t just write code - they validate architecture decisions, enforce constraints, and optimize implementations before committing changes. • Perform deep static and semantic analysis • Refactor legacy systems with minimal regression risk • Generate production-ready code with test coverage • Track performance and reliability impacts This is software engineering at machine speed.