Manicode is a CLI-based coding agent – invoke it in your Terminal and ask it to write code for you. We launched on BookFace last week and got 500 downloads and 60+ upvotes!
It’s a Cursor alternative that’s simpler and frequently performs better. Try it out:
npm install -g manicode
Manicode is different from all the other coding agents, we swear!
Manicode can write code for every tech stack – we know because we’ve built software from full-stack web apps to IoT device firmware.
https://www.tella.tv/video/code-coding-agent-bh6l
To celebrate our launch, we are giving away 2,500 free Manicode credits per month for a limited time to new users!
To claim, 1. get Manicode in your terminal:
npm install -g manicode
2. Run manicode
in your project directory.
3. Finally, enter “login” to sign up and claim the 2,500 free credits.
Also, existing users: you can refer your friends at manicode.ai/referrals — when you refer a friend, you’ll both get 500 credits per month!
Try it out and give us feedback! Check out our website https://manicode.ai
If you have any thoughts, please join our Discord: https://discord.gg/mcWTGjgTj3. We love love love all feedback, positive and negative! Even slightly backhanded ones like this 😅:
So please try Manicode out and let us know what you think!
Better code generation than Cursor
I’ve been working on it since July 4th, which is less than 2 months.
During this period, I’ve spent at least a few weeks completely immersed in building Manicode at ~80 hours per week. I’ve also been juggling responsibilities at Manifold, including interviewing many candidates for a backend engineer position, keeping up 1:1’s with my reports, and attending daily standup to guide the company.
Manicode is your coding assistant: run manicode
in your terminal in your project directory, ask it to do any coding task, and it will make changes to your files.
...and it will do a really good job. Why?
It can grab files it needs for context, edit multiple files at once (no copy-pasting), run the type checker, run tests, install dependencies, and search for documentation.
These abilities are key to doing the best job and will only become more powerful as LLM's continue to level up.
LLM's perform so much better with extra context!
With Manicode, we've come up with this idea to check in knowledge.md files in any directory, and write down extra bits of context, like which 3 files you need to edit in order to create a new endpoint. Or which patterns are being deprecated and which should be used. Or which directories can import from other directories.
Every codebase has lots of implicit knowledge like this that you have to impart to your engineers. Once written down, it makes Claude really fly! It's truly a night and day difference.
You're chatting with it. It takes ~30 seconds to get back to you and then you can tell it what you want to do next or what it did wrong.
This keeps Manicode on track and aligned.
The flow of using Manicode is:
Ask it to do something
If it fails, point out its error
Manicode fixes the error and automatically writes down how it can improve for next time in a knowledge file
You push the commit, and now Manicode has become even more capable when the next engineer runs it in the codebase.
This is the magic loop that will make Manicode productive for experienced engineers in giant codebases.
We can use as many parallel API calls with as much context as we can to produce the best code, because we know that the alternative is human labor, which is much more expensive.