And as I said, this whole project was 100% done by me in my spare time, with zero money behind it, and no real plan for what happens to it now!

If you like it, please spread the word, as I don't have a marketing budget! If it manages to get a big enough userbase then hopefully I'll be able to figure out some way to make it a full-time gig, as it's been really fascinating to build!

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...

Thank you for building software made for actual productive usage instead of weird ricer clout and other performative nonsense.

> Yes, it's another AI coding agent. The industry definitely needed one more.

It actually does need more of them. The current count of harnesses that don't suck is a float somewhere around 0.3, maybe.

Keep doing what you're doing!

I'd love to have software that is actually made to solve problems instead of somehow pretend-granting me some identity. Or just being made by people with no taste in general.

My god the agent harness space is so bad. As if no one in there has ever seen a software in their whole life.

I’ll try it and maybe I’ll be inspired to make my current home brewed agent more document focused again.

One drawback is much higher token usage because we get a very good saving in the cached data.

A little heads up: in your web page, the header download button force double screen with on mobile (iPhone 17 pro). No big problem but always an annoying when a page scrolls in two directions.

~~edit~~

wait, are you doing that? Love JUCE btw

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?

Sold, this is my biggest annoyance with Cline.

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.

Double sold

As a longtime sound engineer I'm pretty familiar with JUCE and your other productions, so I will be trying this with confidence.

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.

The post talks a lot about what this is and how it works. I'm curious, from your usage of it, how does it change your way of working with the LLMs? How does working with it go differently from Claude Code?

Specifically: Everything is a tree. That's interesting, but how do you end up using it? Attack the same problem different ways?

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.

Edit: seems like the remote connection feature may not work...

I really like how easy it is to verify exactly what happened on each tool call, inspect the thinking blocks, etc.

Thank you for building this!

Got fed up with Zed, Cursor, and the other GUI agentic tools and created a console TUI agent for my own use.

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.

For example, I have my codex pointing to the CPA endpoint and the actual running model is a openai compatible one from an specific provider with specific base URL. I hope this could be considered add into roadmap.

Awesome.

> AGPL

Even more awesome.

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!

``` 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.

There's a sqlite CRDT: cr-sqlite,: https://news.ycombinator.com/item?id=41921992

vlcn-io/cr-sqlite: Convergent, Replicated SQLite. Multi-writer and CRDT support for SQLite https://github.com/vlcn-io/cr-sqlite

Notes on sandboxing agents: amla sandbox, agentvm, bwrap at least; debugging mcp servers, and signing agent traces in a standard format: https://news.ycombinator.com/item?id=48893850

--

Can juggler: Design and verify a guitar effect pedals and a wavetable synth with JUCE on a low power chip?

JUCE on embedded controllers; Rust embedded RTOS-like features, a DSP and low power draw:

> Ambiq Apollo4 Plus | ARM Cortex-M4F | ~4–10 µA / MHz | more efficient than an RP2040 Pi Pico. The hardware FPU handles audio math at a fraction of the power footprint.

> STM32U5 Series | ARM Cortex-M33 ~110 µA / MHz | energy-saving modes, math accelerators (Cordic for sines/cosines), audio peripherals

> STM32L4 Series | ARM Cortex-M4F | ~100 µA / MHz | mature, ultra-low-power, robust I2S audio support, sleep state

grame-cncm/faust: Functional programming language for signal processing and sound synthesis / [that compiles to microcontroller DSP code, LLVM IR,] https://github.com/grame-cncm/faust

Then a Rust-based OS for microcontrollers; to isolate devices and device drivers from other processes;

I'd like to learn this too (so this is worth researching)

Rust packages for DSP:

embedded-hal, embedded-io, rand_core

Navigating the Embedded Rust Ecosystem https://www.theembeddedrustacean.com/p/navigating-the-embedd...

https://google.github.io/comprehensive-rust/bare-metal/micro...

hubris > Flash instructions already mention an STM32 F but not yet U or L: https://github.com/oxidecomputer/hubris#flash

Task: Add support for STM32U and STM32L to hubris

"Navigating the Embedded Rust Ecosystem" https://www.theembeddedrustacean.com/p/navigating-the-embedd...

The micro:bit has a speaker and something like a DSP and rust support, though it's not going to run JUCE and BespokeSynth ; kk Just rtic, cortex-m-rt, and nrf52833-hal (for micro:bit v2) might be sufficient but there's already microbit_bsp:

microbit_bsp is a board support package (BSP) library for the micro:bit v2 and newer: https://docs.rs/microbit-bsp/latest/microbit_bsp/

Another task; Develop and test a board support package for low-power chips for hosting effects from JUCE compiled with or like Faust.

But then contain agent sessions;

e.g. Hubris has no shared memory so audio streams must be shoveled over message passing

--

Back to agent sandboxing;

It looks like WebKitGTK uses bubblewrap on linux unless running in a flatpak, because flatpaks don't have permission to create namespaces so bwrap can't run.

Bubblewraplauncher.cpp: https://github.com/WebKit/WebKit/blob/main/Source/WebKit/UIP...

FlatpakLauncher.cpp: https://github.com/WebKit/WebKit/blob/main/Source/WebKit/UIP...

CF workers support nested agent isolates since 2026-03: https://blog.cloudflare.com/dynamic-workers/

dloss/awesome-agent-sandboxes: A curated list of sandboxing solutions for AI agents https://github.com/dloss/awesome-agent-sandboxes

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.

The thing I'm curious about: once you branch, backtrack, or edit a node in the CRDT tree, how do you reconcile that with the model's linear context on the next turn? If you reconstruct the transcript from the tree each turn, does editing anything upstream blow away provider prompt caching, since the Anthropic/OpenAI caches key off an exact prefix match? That's the tension I keep hitting: tree-shaped editing is exactly what you want for control, but it fights the flat-prefix caching that keeps long sessions cheap and fast. Curious whether you just eat the re-cache cost or do something cleverer.

Either way, Miller columns over a doom-scroll is the right instinct. Nice work.

When you fork a sub-thread, does the model get the full parent context up to the branch point, or can you trim what carries over? Context bloat across a lot of branches feels like the hard part.