Limitless used to be Rewind that maintained one of the most useful pieces of software on my Mac, and I use a cracked version now because I refuse to give it up. There is nothing else like it yet. I seem to recall some other thing that aims to be similar, but that might be cross-platform or otherwise Linux-ish which discounted it as a practical alternative. (I don't remember its name unfortunately)
Does it spoof the Bun authentication/signing? If not, this will eventually stop working once Anthropic cuts off access from versions of Claude Code that don't sign their requests.
I'm getting a little fatigued by all the harnesses that are made by other coding agents. Like, when I checked out opencode, it looked and felt incredibly impressive, until I looked at how frequently it completely invalidated the KV-cache. After looking at the source code, it's basically unsalvageable and I ran far far away. (It's mostly imperative garbage which is typical of undisciplined agent output. It doesn't even use React, it uses some other reactive library in a non-declarative way, I think SolidJS)
DeepSeek Reasonix is better in terms of cache stability because that is a core tenet, which should honestly be table stakes for agentic tooling, but the TUI is kind of ugly and the tools also kind of suck (they pretend the sandboxed working directory is at /, which makes the model almost unable to use MCP servers that expect to be passed filesystem paths). On top of that, it doesn't expose the structuredContent of MCP server tool responses, which is like... the entire point of it? Now all my tools that return huge swaths of JSON data into structuredContent, which Claude Code can process perfectly fine, need an additional separate path to generate readable versions of it into content because Reasonix ignores structuredContent for some reason. That's supposed to be the model-side output, while content is the user-side output, but whatever.
I don't know how much more of this I can take. I'm in the process of working on my own harness essentially from scratch, manually, because I'm so fed up with all this vibecoded tooling that misses incredibly basic and obvious design.
I feel like Claude Code used to be from scratch like this and that was why it was so good, until they started vibecoding large swaths of it and stripping away all the power-user features and good taste that made it so wonderful before. Now it even has random, inexplicable problems like "API Error: 400 messages.1.content.15: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response." which shouldn't even be able to happen!!
And like, I get the distillation angle of why thinking output was completely removed from Claude, but I work in bypass-permissions mode and I want to correct misunderstandings as I see them. This is different than wanting to review each edit.
Speaking of reviewing each edit, I hate that Reasonix doesn't print diffs, and just says "use git diff". Like, no? I want to see each change the agent made and when. I don't want to only see one diff at the end; that nearly ruins the point of conversation history.
Having just started out building my own harness because I don't like the others, I really resonate with this post. You probably should make a harness, it seems you've got a really good approach and a great understanding of what it should have.
I mostly still like Claude Code, but I agree it's getting buggy and bloated in their need to move so fast. With the June pricing changes I felt I needed to build an alternative quickly just in case, and so I can start looking at other models for my "claude -p" usage.
The videos from the makers of Pi are interesting with some useful information, but ultimately I came away deciding I would never want to use Pi.
It also helps that Pi & most harnesses don't work on a lot of older computers systems I'd like to be able to use a harness on. It's just API calls, there's no reason this shouldn't all work on much much older machines.
I have not tried pi! I heard of it, but I didn't look into it because Anthropic is cracking down on third-party harnesses by making them prohibitively expensive. I suppose though now that I have a DeepSeek API key due to Reasonix I can give it a shot. (even the pro model is so cheap!! I've been using it for days on multiple projects and have barely spent $1, and I think it can go much further with better prompting.)
As for advice, what kind do you mean? Do you work on Pi?
Good talk! I'm using Claude to clean up Pi a little bit before I try it (porting to PNPM is part of my standard startup checklist); I'm very excited to see how it goes!
No, I just was curious to know how you found Pi; I've got so much from pi + DS4 pro that I think I am done feeling bad about Anthropic limits. The cost is ridiculous, but I wonder if there's even a lower floor with reasonix or DS4-specific pi config
I saw Pi on the front page of Hacker News a few weeks ago, I think.
Anyway, I've been trying it for the past day or so and I must say, this is awesome. The extension functionality in particular is great news at least. But there's a lot more to love that seems to actually have been tastefully crafted by real people; a lot of power-user features that would fly right over most agentic implementers, such as branching on the level of individual tool calls rather than only by user messages as in Claude Code. It feels incredibly good, I am very happy with it.
I've deliberately been post-poning harness building.
I think it's great as an obligatory learning experience.
But I'm hoping someone will come along and provide the "best of breed" harness:
- OpenCode's TUI and client-server model,
- Claude's prompt engine,
- Pi's extensibility, and
- the codebase stability of a craftsman (yet to be seen).
I haven't tried other harnesses than those three. It's time-consuming, and does not align with my primary goals.
I've been reimplementing a TUI library based on Ratatui, but drawing the UI components of OpenCode's OpenTUI and a bunch of Ratatui-adjacent components. Was hoping someone would separate the concerns and reverse engineer Claude's prompt engine and just not provide a UI for it. Make it modular so each part can be replaced by something better. There's only really 3 parts: TUI library, engine, and client-server (so you can choose between web or terminal, and so you can host the engine + server in the cloud, resume your sessions, and whatever enterprise features you want for session and memory management.
surely concats of user input, stdout of external dependencies, and non-deterministic output feeding back directly to an eval is safe. it's never been a problem before. not even trying to check the boxes when it comes to security anymore.
Being vulnerable makes money unfortunately. And making money now has always been seen as more important than being sustainable in the long-term. Even if an exploit later takes away every cent of earnings.
> Sorry, but we couldn't find data about this flight.
https://www.flightradar24.com/data/flights/ua236
reply