Загрузка видео...

Не удалось загрузить видео

На главную

Just open sourced Monocode - a desktop UI for your coding agents. Works with your existing Claude Code, Codex, Cursor, and OpenCode harnesses. Tabs can be sessions, a lightweight editor or a terminal. Currently only supports macOS Apple Silicon. Still very early so expect bugs. Feedback and small PRs...

53,624 просмотров • 1 месяц назад •via X (Twitter)

Комментарии: 70

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

link to the source

Фото профиля zifu
zifu1 месяц назад

When will Pi support come?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

Working on it :)

Фото профиля zifu
zifu1 месяц назад

Thanks! Also, will you ever release your agent macos status bar project as well?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

Ahh yes 😁 need to clean it up a bit

Фото профиля Apollon Foivos Bakis
Apollon Foivos Bakis1 месяц назад

Having one UI across different coding agents is really useful.

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

certainly and its not a new idea... many alternatives out there :)

Фото профиля Jakub Łapeta
Jakub Łapeta18 дней назад

Are you thinking about mobile app? It would be great to see one! When it comes to bugs: sometimes if I switch models inside one session the second one can’t load the context of the conversation. It happened when I used Fable for planning, few tasks and later switched to sonnet

Фото профиля Nikolay Petkov
Nikolay Petkov18 дней назад

Yeah I just discovered it as well it’s a bug and it’s fixed in The latest commit… I will make a release in a couple of hours s

Фото профиля Jakub Łapeta
Jakub Łapeta18 дней назад

What about that mobile app? Are you planning one?

Фото профиля Nikolay Petkov
Nikolay Petkov18 дней назад

yeah, definitely. i want to get a few other things right first before the mobile app

Фото профиля 丂ムんノレ
丂ムんノレ1 месяц назад

linux when?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

Soon :)

Фото профиля 丂ムんノレ
丂ムんノレ1 месяц назад

umm i made the change and it work in linux

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

thats awesome, you can open a pr if you want but please check CONTRIBUTING.md before you do fyi I am the only maintainer :)

Фото профиля 丂ムんノレ
丂ムんノレ1 месяц назад

sure sure i will do build check

Фото профиля Ben Mo
Ben Mo14 дней назад

man this is brilliant!

Фото профиля Nikolay Petkov
Nikolay Petkov14 дней назад

thanks 🙏

Фото профиля Coach Mov
Coach Mov25 дней назад

context 창이 계속 그대로야. 새로운 세션을 만들어도 초기화가 안되는 현상이 있어.

Фото профиля Sandeep
Sandeep17 дней назад

when can i expect a windows version or is it already out there? sorry the github instructions were not so clear hence clarifying

Фото профиля Nikolay Petkov
Nikolay Petkov17 дней назад

Yeah windows is out check the releases page

Фото профиля Sandeep
Sandeep17 дней назад

thank you. one more clarification: is there any telemetry or logs that you are centrally logging? just checking from an enterprise usage standpoint.

Фото профиля Nikolay Petkov
Nikolay Petkov17 дней назад

No none :)

Фото профиля Basil Khowaja
Basil Khowaja1 месяц назад

Does it support file manager inside the app so I can view almost all files in a specific project path that i open up?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

Yeah it should also auto update if the agent is currently adding or deleting files too

Фото профиля Basil Khowaja
Basil Khowaja1 месяц назад

Ahh, I see. When do you intend to release linux supportV

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

there are still bugs i want to iron out but linux support is coming :)

Фото профиля Buswe
Buswe1 месяц назад

Tabs as isolated sessions is the sneaky-good part, two agents can't share state and step on each other while you keep both in view.

Фото профиля probe
probe1 месяц назад

Tabs as sessions is the part I want most. Jumping between a terminal and an agent run in one window is where my setup gets messy, so this fits nicely.

Фото профиля Francis
Francis23 дней назад

Incredible UI and the performance seems great so far. Curious how you are thinking about workspaces. So far I cannot see a way to create them within the app itself.

Фото профиля pdp
pdp1 месяц назад

It is beautiful.

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

Thank you :)

Фото профиля Paresh Dudhat
Paresh Dudhat1 месяц назад

Looks pretty clean ui. Also building something similar. Just want to know why you chose Tauri?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

mostly for size and speed... monocode is 25mb while similar electron apps are 500mb performance so far is pretty great as well but you could probably achieve the same with electron... idk

Фото профиля elias
elias11 дней назад

Super cool. Mobile app?

Фото профиля Nikolay Petkov
Nikolay Petkov11 дней назад

on the roadmap... in the next couple of weeks i would say :)

Фото профиля Andika
Andika28 дней назад

This is great! Will u someday make it like agentic chat UI similar like grokbot? That'll be interesting

Фото профиля Nikolay Petkov
Nikolay Petkov28 дней назад

that would be probably a project on its own

Фото профиля Andika
Andika28 дней назад

interesting, can’t to see that future project started! keep up the good work🙌

Фото профиля uhhexe
uhhexe22 дней назад

What exactly is this? Looks insanely useful. Is this a coding environment? Looks great

Фото профиля Nikolay Petkov
Nikolay Petkov22 дней назад

its a GUI for your coding agents... if you already use codex, CC cursor and many others you can run them in Monocode so you dont have to switch apps or terminals not a new idea i just built it cause i wanted something for myself

Фото профиля Thomas Nguyen
Thomas Nguyen1 месяц назад

So it like cmux, conductor, can we orchestrate, spawn lanes?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

not currently but definitely sth i am thinking about

Фото профиля Dan
Dan28 дней назад

Is it like @orca_build but early stage?

Фото профиля Nikolay Petkov
Nikolay Petkov28 дней назад

@orca_build it depends… if the main idea is to work with multiple harnesses from one interface then yes

Фото профиля Lily|AI×自動化×マーケティング🤖
Lily|AI×自動化×マーケティング🤖1 месяц назад

タブがセッションにもエディタにもなるの便利そうですね。僕もClaude Code複数走らせて見失うので試します

Фото профиля Felipe Orlando
Felipe Orlando1 месяц назад

looks amazing... two things that any other app miss for me are: - orchestration, like Orca has - spaces (personal, work, oss, etc), like... Arc?

Фото профиля 安叫兽|Bird🕊️ 🔶 BNB
安叫兽|Bird🕊️ 🔶 BNB1 месяц назад

标签页能混开会话和终端,这个思路挺顺手。

Фото профиля Rayel
Rayel1 месяц назад

Are you planning to support grok?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

yeah grok is next! funny enough it was in the initial version of the product but i scrapped it

Фото профиля a
a28 дней назад

When windows support?

Фото профиля Nikolay Petkov
Nikolay Petkov28 дней назад

will review today

Фото профиля Wim
Wim1 месяц назад

What makes it different from e.g t3code? Any plans to support pi or omp or GitHub copilot?

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

i would say the same like t3code and in all honesty t3code is probably more featureful pi coming next... haven't thought about omp or copilot

Фото профиля Wim
Wim1 месяц назад

Would recommend. Everyone else is already doing Opencode, Codex, Claude while a lot use pi or omp. Copilot is great too, although people bash it because it’s GitHub but I probably like it the most. Just my 2 cents

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

i agree. also i was an early Copilot customer and it was pretty good but their price hike made me switch over

Фото профиля Wim
Wim1 месяц назад

Have a look at copilot SDK

Фото профиля Ihor Kolobanov
Ihor Kolobanov25 дней назад

Nice, congrats! I'm building - similar idea, but built around multi-harness workflows: Claude Code plans and delegates, Codex implements, opencode reviews. Are tabs staying independent by design, or is cross-session coordination on the roadmap?

Фото профиля Nikolay Petkov
Nikolay Petkov25 дней назад

thanks warpforge looks cool not sure yet but orchestration is definitely on the roadmap

Фото профиля Ihor Kolobanov
Ihor Kolobanov25 дней назад

Cool, will be watching. Happy to compare notes when you get to it

Фото профиля Barth
Barth1 месяц назад

Looks pretty nice! I'm desperately looking for the perfect tool to orchestrate all my agents from Cursor, Codex, Claude and OhMyPi. Tried many ADE like Superset, Orca, Conductor, Paseo, T3 Code etc. but only herdr can do what I want for now, but I want something nicer to use.

Фото профиля Shreyansh | Building AI Systems
Shreyansh | Building AI Systems1 месяц назад

A shared interface for coding agents could reduce tool switching, but the durable value is a consistent review surface. Plans, diffs, commands, tests, and approvals should look familiar even when the underlying model changes.

Фото профиля AI Mastery Guide
AI Mastery Guide1 месяц назад

That UI looks super clean

Фото профиля maddada • ghostex.dev
maddada • ghostex.dev25 дней назад

Looks great man, very polished and smooth ux. I'm like a year into the ADE journey and my honest advice is it's not worth it 😂 There's like 1 billion of them and it's impossible to make money working on yet another ADE. Also the adrressable market is somewhat small. If you really want to keep implementing then send me a dm I can share stats about what people actually use so you focus on those things :) All the best.

Фото профиля Jul.io 🇩🇪
Jul.io 🇩🇪20 дней назад

Man it looks great! What about the performance, RAM, CPU Connectivity using SSH?

Фото профиля Thomas
Thomas1 месяц назад

yet another mac only app

Фото профиля Nikolay Petkov
Nikolay Petkov1 месяц назад

sowwy 🥺 linux and windows coming soon

Фото профиля LocalAIMaxxer // Niko
LocalAIMaxxer // Niko25 дней назад

My Bulgarian brother, surely you can't have the landing page like this in the age of AI. I want to see more about Monocode

Фото профиля Nikolay Petkov
Nikolay Petkov25 дней назад

in the age of AI you don’t need a landing page 😊 Jk I will do it at some point

Фото профиля LocalAIMaxxer // Niko
LocalAIMaxxer // Niko24 дней назад

Add it! And let's link up at some point, I'm also Nikolay, in London, working in AI.

Похожие видео

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

289,832 просмотров • 9 дней назад

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Akshay 🚀

116,880 просмотров • 7 дней назад