RU version is available. Content is displayed in original English for accuracy.
I'm a long-term C++ dev, and over 30+ years I've created some successful audio dev tools (JUCE, the Tracktion DAW, the Cmajor DSP language). All of these came from me getting annoyed with something I had to use, and deciding to have a go at my own take on whatever it was.
So Juggler is my attempt at an AI code agent, after spending too many hours loving what the models could do, but hating the CLI experience, and having some opinions of what a better UX might be for this stuff.
Lots more blurb on the website and github, but a quick tech dump which might grab your attention if you're into these things:
A session is a document, not a log file. Each conversation is a Yjs CRDT tree. It can branch into sub-threads (recursively), and you can drill down, backtrack, edit, undo/redo, and inspect everything: tool calls, approvals, and the raw context JSON going to the model, etc. The UI is based around Finder-style Miller columns rather than a big doom-scroll, and is quick to navigate.
Because it's a CRDT behind a local web server, multiple clients can attach P2P to a live session: the native desktop app, a browser tab, or your phone. Run the headless server on the box where the code lives, view it from wherever.
Almost everything is a JavaScript plugin: every item in the context (read/write/bash/etc.), the LLM loop strategies, slash commands, and their UIs. You can inspect, fork, or replace any of them. I don't do much agent customisation myself, but lots of people do, and I'd love to see what they think of with this plugin API.
Go backend, Wails for windowing (no Electron), plain type-checked JS (strict JSDoc), Yjs for the documents. Usual BYOK provider support: Claude (CLI or API), OpenAI/Codex, Gemini, Ollama, OpenRouter, DeepSeek, etc.
The app's AGPLv3; the extension SDK and bundled extensions are Apache-2.0, so extensions have no copyleft strings attached. No signup, no telemetry, trying to make it frictionless for people to try it out..
It's very much a beta, and is a one-man side project. It hasn't yet had a proper kicking from the real world, but I'm confident some people with similar preferences to my own will like it!
Discussion (51 Comments)Read Original on HackerNews
I think that’s the secret to stability. I see too many projects that try to embed the harness into their UI. I think that’s completely wrong because it leaves no interface for changing or reasoning about the system.
The harness needs a lot of love and it should be as small and as possible (at least somewhat). I dream of a world in which we have some standard interfaces here, including for the UI.
I've got my own attempt with OrcaBot (short for orchestration of bots). It's also been a 6 month solo build experiment. I'm not trying to plug.. just that I'm also neck deep in Steve Yegge's Stage 8 AI-assisted coding chart and understand how much thought and effort went into this.
Thinking about where this is all going with talking to AI like fully autonomous employees similar to @Claude can you see a comms app type approach that combines something like slack with your tree/thread structure? It's somewhat orthogonal to your "inspect everything" but could intersect by bringing click through/open in options...
However I see all those people out there trying to build these huge agent orchestration schemes, and if juggler's extension system can do that (or could be made to do that with a few tweaks) I'd be really interested in helping that to happen
But with regard to Juggler and orchestration, have you seen "claude agents" (started in the terminal as claude agents instead of just claude). I ask because your tree like approach has similarities to how claude agents manages claude agents/subagents doing tasks with the ability to drill down in to each at a time which is why for me its not such a leap from what you already have.
~~edit~~
wait, are you doing that? Love JUCE btw
Another really elegant thing that pops out of subthreads is that to do a compaction, you simply move the entire conversation into a subthread, and let the subthread summarise itself (which they do anyway). So we get compaction as part of the architecture, and you can also dig into that old thread if you need to revisit any of it
I’m generally happy with my agent and want to keep that, but I do think the UI could be better and this looks like a neat step that way.
On the site you also mention being pretty opinionated about the tools you use / build, which I imagine is part of the reason why you spend more time on this before releasing it. What was your experience using ai to build a larger project with a very specific idea / taste in mind?
Surprisingly, I've really enjoyed the experience. I have friends who lament that they probably won't be hand-writing code much more, but although I've always loved the craft of coding, I discovered that a lot of the fun I get is just in the end result, not how I got there.
While I've put huge effort into things like its architecture and extension API, it's really trying to just build a lovely UI/UX that has been my motivation on this.
I've settled on JUCE as my cross-platform app framework (not just plugins) of choice, so it'd be interesting to hear about your experience with building this app out .. could you tell us a bit more about the architecture and any impactful decisions you made along the way with regards to tooling/integration? Is there now a juce-go-module or something like that, which you've wired up to JUCE' web view functionality?
There's no c++ in it, it's all Go/Javascript. And all the UIs are HTML. JUCE is a great choice for some things, but this wasn't one of them!
Got fed up with Zed, Cursor, and the other GUI agentic tools and created a console TUI agent for my own use.
But TBH I think a lot of the GUI agent tools so far have been pretty much terminal apps wrapped in a thin GUI layer, which is why they don't seem to add any value over just doing the same UX in a terminal
Also when I opened a new session (in the Juggler GUI) at my root where all my projects live, my instinct was to navigate to a project directory first or to have it open there. Not sure how to do this, without changing the global setting for my projects root. That's how I think through claude code/codex coding sessions via the terminal wondering if that mental model is wrong.
I asked which skills it could access, and it turns out it couldn't access any of my global skills already - I thought that part would just work since it accesses my codex subscription. is that something you plan to add.
In terms of who might be interested in this: I've watched amazing communities spring up around open agents like Opencode and Pi. People are getting into those because of their extensibility and being model-independant. They're great projects, but like many people I know, I really hate being stuck in the terminal for this kind of tool. I also had some ideas around what an agent's UX could be like if every item in the context was a plugin (with its own custom UI).
So I guess if you're a claude/codex user but want to escape the terminal (and let's face it, their GUI apps are also basically the same UX as a terminal but with nicer fonts), I'm trying to do something different here, would be really keen to hear what the enthusiasts think of it!
I mention all this to say someone like you picking up the desire to build an agentic platform really piques my interest. Right now I am using Opencode for most of the stuff I am trying to do at $WORK and it does a good job on the whole at having sufficient functionality. But the release pace is blistering and it does feel bloated - both in terms of functionality as well as system prompts.
Moreover, I observed all of the same issues you mentioned and certainly wanted more of a tree like experience as well as a more UI forward experience. In order to get the functionality I wanted (good worktree support, sandboxing, etc) I eventually just had to let go of using opencode's UI and embrace the TUI because it was the only thing I could embed into a workflow that let me set up all of that in a sane manner. But problems still remain with the "doom scroll" experience when to your point clearly a tree based experience would be better.
I was ready to just settle with my cobbled together opencode flow and maybe migrate to Pi later on and just accept i'd have to roll my own GUI harness for my nontechnical team members. But seeing what you've put together so far (and knowing it's you who wrote it so I'm probably going to just see a step function level better quality in architecture/efficiency) is going to make me reassess in a good way. Some things that I'll be considering:
- Worktree support
- Sandbox support
- Skills/subagent handling
- Hashline based editing (feel like this is a huge part of why people get better results from pi/omp over opencode/codex/claude code)
- Ability to customize tool calls + have rich embeds
- Web UI support (if i'm building this out for team members, native GUI can get messy and web client is ideal)
- Long horizon efficiency (IE i regularly get to 200k-400k context length sessions; while the model handles it fine, opencode gui will get laggy while the tui keeps chugging along)
For a lot of this stuff, it's less critical that all of this works perfectly out of the box and more critical that the architecture makes it easy to build (ie as with Pi ecosystem). What I'm after long term is something a bit like https://github.com/ColeMurray/background-agents in capability but without the overly tight coupling and design decisions that product has made.
The way I want to get there is to find the right base (whether that's Pi, OpenCode, or your project Juggler) and build the background agent harness layer. Previously it was just Pi and OpenCode and neither was really perfect (GUI story was probably the weakest for both) but it's great that I have another option to diligence that might actually be a better fit for what I'm trying to do.
Excited to see how this develops and kick the tires on it myself. The tree paradigm feels like the killer feature to me; not sure of anything else besides pi/omp that has it.
I've got things like worktree/sandboxing/skills on my TODO list.
I'd heard of hashline based editing - I will dig into that, and it's probably easy to add, though TBH I've not had any hassle with the editing tools so far.
If you get stuck into customising tool calls + their UIs, would love to hear how you get on, as that's one of the big goals for this. I've implemented all the built-in tools as plugins so hopefully it'll cover everything you need.
In terms of long-horizon stuff, yes, I also often hit 3-400k and haven't had any issues, but let me know if you spot anything untoward
``` LLM error: POST "https://api.deepseek.com/v1/chat/completions": 400 Bad Request {"message":"The `reasoning_content` in the thinking mode must be passed back to the API.","type":"invalid_request_error","param":null,"code":"invalid_request_error"} ```
I'm unsure about putting my Anthropic key in there as I've lost track of what they ban you for or whether that eats money from outside of my subscription.
Oooh, and nicer support for codefences would be good.
Cool project actually, but I noticed the author said "No Electron" as if Electron is synonymous with JavaScript.
My biggest concern about it actually is using Go to render web front-ends in HTML/CSS hahah so I'm not sure "No electron" is selling me.
I come from a hardcore, real-time C++ background and the idea of a product not being a single self-contained binary is just too far for me to go!
(But I don't think the choice of JS back-end should make the slightest difference to anyone using this. I could swap electron in there in the future and probably no-one would notice)