I'm was closing a day of work and it stopped in the middle of a long plan, I started codex and tell it: "I was in the middle of work with Claude could you read the plan and the session "x" in ~/.claude and continue the work" it just completed everything :D
I’m working on a project that makes switching between coding harnesses essentially unnoticeable. It’s particularly useful when I run out of credits on any given day
The entire platform is skill driven, and based on the premise that state is your local file system. That makes switching harnesses so easy
It’s all open source and has plenty of other features, including inter agent communication, telegram client and much more in the pipeline
Not sure what the problem with switching is? When I run out of my kimi session, I just switch model and tell deepseek to continue. Yes I eat the initial cache miss but that's it, no fancy harness required.
I think having a codebase that can use any harness is the optimal setup. I often switch between harnesses and models all the time at work. We have our state/spec stored in git, so we can pack it up on friday and start fresh on monday. Or more commonly, using gemini/opus to create rich specifications and using Luna to implement them. Then switching again for reviews etc.
No project needed man. There's also a whole ycombinator company for the same thing, skillsync, also useless. These things are either out of the box or they are 2 prompts away.
I started using Pi with Astra on a whim after really enjoying Astra and reading somewhere that you get close to identical results as with the codex harness but for a significant hunk less token usage.
Coming from mostly using Claude models, the terse factual statements coming from Astra via the Pi harness are a breath of fresh air over having to wade through the flowery verbose nonsense that Claude constantly outputs
I recently had Astra review a fairly detailed design doc I have for an audio VST fork, that I originally wrote with Opus and/or Fable a few months ago. The doc reaches deep into signal flow and module topology while lifting most of the DSP code from other open-source projects. I had it review for feasibility and architectural soundness.
Astra found a number of flaws that would have come up during implementation and we worked through them. But then I had Fable 5.1 review that document and it found a number of issues with Astra's changes, the least of which had was that Astra duplicated a lot of technical notions that it added rather than using references to an authoritative section. It also flagged some of Astra's designs as technically impossible, pointing out why and I'm actually in the process of digesting its feedback and updating the design spec. (I hand-review each point and we work through a solution together -- I don't trust either model to come up with something that follows my vision on their own)
I'm not promoting one or the other, I just found it interesting how this sort of adversarial review found pretty significant flaws in the other model's work. I am curious as to whether this process will eventually converge on a document that both agree on or if the models are going to perpetually nitpick each other.
I haven't actually started implementation yet, so maybe one or the other is full of shit. Just trying to come up with an architecturally sound design for something I want to write, when I lack the DSP knowledge to be able to write it myself. But the intent is to pass an agent the design doc and list of milestones and let it handle implementation.
In my experience, rather than converging, you end up with a minced up concept. You have to know when to stop the loop. I filter the feedback too, and need to challenge some of the challenges as these models tend to be very conservative. I believe this is intentional, to control AI psychosis, which is indeed quite easy to get. My 2c. If you don’t have good control of what you’re working with you are either searching blind or end up with something basic.
Agreed, I believe strongly that human-in-the-loop is the way to go. LLMs are fantastic thought partners but ask it to critique something and it will go absolutely nuts. For Claude Code's /code-review command the highest I will set it is 'medium', otherwise it will produce so much feedback that you'd never get anything done.
1. I go direct to source, i.e. DS platform, I find it cheaper than paying the openrouter tax -- I also switch it up a bit
2. I built a local LLM router, that I update with new profiles that have my preferred provider of the week (lowest token costs/speed) with fallbacks, like mimo --> DS4 etc.. if there is overloading,
3. I use 3 diff harnesses, CC/Codex + Opencode -- they all talk to each other through a custom rig system that routes messages between llms using a Rust backed structured JSON system
Not saying this is the best, it's just what I like and works for me^.
I can flow quite naturally between Opus/Astra/K3/GLM/MiMo/DS/etc.. this way and often do...more so these days with subs no longer great as they used to be.
I don’t understand your point or why people are upvoting this. I’ve done this between many different models. Did you just discover that a frontier model can read context? I genuinely don’t get your point.
I’ve had to have Claude agents pick up codex’s context after it hits one of its “cannot connect” issues way more often than the other way around.
In CC, "/exit" will tell you how to --resume <session-id> upon exit. This will eat zero tokens, and it actually does not require an active internet connection.
`claude --resume` will list your sessions, you can copy the title. Codex may just list and grep the sessions files in ~/.claude and filter the one with the name.
I also have the habit of naming my sessions with `/rename`
I have an 'ask' alias in my shell that just uses Haiku. I use it daily for pretty much everything
For more long work, I now use Fable to create a PLAN.md. I tell it to make a plan that will be executed by other models, and most of the time it ends up choosing Opus or Sonnet.
I didn't start doing this recently. Before that, I would just use the top model for everything. Splitting the work across different models depending on the task has helped a lot. They run faster, and I usually get much better results
Great work, and thanks for sharing the transcript! Just skimming through the chats, I've already learned a lot. Would be so awesome to have this for any region/city, but that is a data problem to solve.
This was posted on HN a while ago and I started using it then. I've accumulated quite a bit of data and have used both export and import. That's turned out to be the most useful feature for me
I've used other trackers, ones focused on CBT. My only suggestion is to allow text notes in each entry, so I can track emotional states or recurring thoughts
GitLab is probably the most reasonable alternative. I migrated and it took me some weeks to adapt to the new CI, but for my use case it's basically equivalent in features.
I started with the cloud version, then moved to self-hosted because it wasn't a big effort for our team. We also reduced our monthly invoice by about 50% after the move.
The product is being launched before the value is clear.
We've seen similar waves with new technologies before: overexposing the pros, dismissing the cons, hyper-optimism, and people using a lot of jargon without saying much of substance. The difference this time is the scale of the impact and the volume around it.
Senior full-stack engineer & tech lead, 10+ yrs, Python/Django-first. I ship MVPs that reach production and stabilize/modernize legacy systems without breaking what works. Comfortable across backend, frontend, and infra.
Strong on SaaS, integrations and data flows: Zapier apps (Platform/CLI), ERPs, billing, CRMs, webhooks, ETL — plus LLM integrations (OpenAI/Claude). Years spent making systems talk to each other reliably.
Ex-Zapier (integrations), ex-Tesorio. Experience across SaaS, fintech, and e-commerce.
Senior full-stack engineer & tech lead, 10+ yrs, Python/Django-first. I ship MVPs that reach production and stabilize/modernize legacy systems without breaking what works. Comfortable across backend, frontend, and infra.
Strong on SaaS, integrations and data flows: Zapier apps (Platform/CLI), ERPs, billing, CRMs, webhooks, ETL — plus LLM integrations (OpenAI/Claude). Years spent making systems talk to each other reliably.
Ex-Zapier (integrations), ex-Tesorio. Experience across SaaS, fintech, and e-commerce.
Hah, Im in similar situation, but I am network/IT admin. I think its worse, because who need networking guy? You just plug it in and it works, right? ;)
reply