Developer releases Prospero, a lean C++ coding harness for local LLMs
A new tool for running AI agents with drastically lower memory usage than existing alternatives.
What to know
- Prospero uses ~100x less memory than existing harnesses by combining C++, Dear ImGui, and minimal dependencies instead of web stacks.
- The harness allows AI agents to autonomously call tools, execute shell commands, control desktops with vision models, and spawn subagents.
- Developers in the thread report building their own harnesses to meet specific UX/DX needs, with disagreement over whether C++ is the right choice for UI-heavy agent tools.
The dispute Whether C++ is an appropriate technology for building agent UIs, with critics arguing UI-heavy tools belong in web/text stacks and proponents contending native code ensures resource efficiency at scale. · positions read across 23 posts and comments
Lean, native C++ approach is superior for serious agent workloads due to resource efficiency and stability.
-
“this is has the guts of great enterprise level software. Once you've serious data being thrown at something built on JS and run into OOMs, that's when good old C(rust in the future maybe) stack shows these up.”
gapo · Hacker News ↗
C++ is the wrong choice for agent UIs, which are fundamentally about markdown, HTML, and text flow.
-
“When I was writing a code agent… there's no way I'd have used C++ for an agent GUI!”
julesrms · Hacker News ↗
Existing harnesses have poor UX/DX; developers should build custom solutions for their specific workflows.
-
“Nice to see a gui coding agent. I use tui agents all the time but I am building a gui one. I use Claude Code, Codex, opencode and a couple other but I do not like the DX/UX.”
brainless · Hacker News ↗
fovc Prospero creator
How it unfolded 1 development · click the chart to see its coverage articlespostscomments
-
1
Developers discuss harness design tradeoffs and alternatives
Comments from developers surfaced differing views on harness architecture. Some praised Prospero's lean C++ approach and desktop-focused design; others questioned whether C++ was the right choice for UI-heavy agent tools; several mentioned building their own harnesses to meet specific needs.
“At its core a coding harness is essentially curl glued to popen(). This should not require gigabytes of RAM. So I built my own: Prospero.”
— fovc · source -
Nice to see a gui coding agent. I use tui agents all the time but I am building a gui one. I use Claude Code, Codex, opencode and a couple other but I do not like the DX/UX.I often want click a part of the wall of text (from agent) and search for related text, open them up on the side or so. I want to open a linked file. I want to answer multiple…
2 more of the top 3 · 23 posts in this stretch
-
Nitpicks about CLI coding agents:Many times, while they are doing something, I’ll be typing a prompt, and then all of a sudden I get a question with Y/N options, and by accident, I’ll type Y/N as part of a word thus “answering the question”, many times either steering in the wrong direction or stopping the agentNeither Claude code nor Codex solve…
-
Great to see what you're doing there, but speaking as a 30-year hardcore C++ veteran (to the extent of creating my own C++ GUI framework: https://juce.com)... When I was writing a code agent (https://github.com/juggler-ai/juggler), there's no way I'd have used C++ for an agent GUI!Agent UIs are all markdown, HTML, big scrolling lists, text flow…
-
-
background
Developer releases Prospero coding harness — A developer published Prospero, a C++ coding harness for running local LLMs as agents. The tool uses significantly less memory than existing harnesses while offering features like desktop control, headless deployment, and subagent coordination.
Also covered reported alongside — the timeline has no entry for these yet
-
first by HN Best, 11d ago · also HN Frontpage
What people are saying 19 voices from 1 site · best of 23 · verbatim
- What alternatives exist for developers who want resource-efficient agents but prefer TUI or web-based interfaces?
- How do licensing restrictions on Claude subscriptions affect harness adoption?
- Nov 1
-
I have used Prospero for some work today, and I have to say I really like it! I have settled on a combination of Zed, Pi and Paseo so far, but I'm adding Prospero into the mix from now on.
-
whay would you need more then PI offers? Read Write Patch and shell shoudl be enough, also for GUI
-
Hopefully the agent loop holds up because that's also very important, would be quite a relief moving off harnesses consuming GBs of RAM because they're sending JSON to model provider server
- Oct 31
-
I think agy has a “questions pending “ pattern for waiting questions rather than popups. I don’t like it but sounds like they were solving your issue
-
I recently switched from the OpenCode GUI to OpenChamber, which still uses the OpenCode backend. It's pretty great. One of the features is the ability to select a portion of an agent's response and add a comment to it. Comments are sent along with the next prompt. It's also much better at handling subagents. With a proper plan in place, it will…
-
I'm tired of tech people forgetting to see if something else is using a name: http://www.prospero.org/Way to cause confusion.This is like starting a new country and calling it France.
-
OK, I like this in concept a LOT. I especially like that it's efficient and headless with an attachable GUI.But I don't like how opinionated it is: "Therefore Prospero prime design principle: Never wait forever. Every operation has a deadline. This decision influences everything."I respect that opinion, but I don't share it, and therefore an…
-
I can heartily recommend switching to private local speech to text voice input with Handy.
-
I'm similar but not really a programmer. I've been a linux sysadmin for a few decades but for whatever reason I prefer using Codex via the desktop app rather than the TUI. The desktop app on linux is fine for me. Note: i've not used it anywhere else but since linux was the last to get the desktop client i'm assuming it's at least as good on other…
-
i believe a harness is a personalized thing. everyone should develop their own. doesn't take long to have a working prototype, after that you can extend it as you use it.
-
I see the argument but personally I find LLMs to be a perfect TUI application because of their functionality. Text in -> text out is precisely how the models work so the interface doesn't need to go much beyond that.
-
Many make their own harness today anyway...I did mine as well and that takes 4% the resources of opencode and in a similar tui style.I think it's great and everyone should make their own.
-
You're not alone - I also revolted against the TUI crowd and created my own GUI-centric harness juggler (https://github.com/juggler-ai/juggler). Might be up your street. If you're not too involved in your own project, maybe help out on mine :)Honestly, I just don't get the TUI obsession, other than the fact that people are multiplexing many remote…
-
There are so many Prosperos already. Why choose a name that is so heavily overloaded?
-
As a counterpoint to a lot of the comments on this now portraying this as dated and questioning the stack behind - this is has the guts of great enterprise level software. Once you’ve serious data being thrown at something built on JS and run into OOMs, that’s when good old C(rust in the future maybe) stack shows these up.Love to see such a strong…
-
A year ago I never felt my MacBook was short on resources, but these days I find myself thinking a lot about the performance of harnesses and agent tools.
-
There are so many cool harnesses I could use if I didn't have an outrageously subsidized Claude subscription
-
If you're looking for an agent implementation that is light on resources, but prefer to work in a terminal, consider also hax (https://usehax.dev/). Less than 2 MB fully static Linux binary, few MBs of RAM use in runtime. Works great with local models also (auto-detects config from running llama-server), besides the usual cloud providers.
-
What a beautiful and space efficient UI. I love Dear ImGUI and the people that build interfaces with it.Reading through the whole post, this sounds like an thoughtfully and intentionally designed product. One with strong opinions and the developer’s real lessons behind it. In the current era of slopware- especially around AI tooling - this is…