robbomacrae

“so the API use is in addition to the subscription, but it can't be helped.” - I beg to differ. OrcaBot.com is a claws that runs using vanilla Claude Code so you can do all that with your regular subscription. Disclosure: I’m the author. The only reason these other claws can’t offer that is because they front it with their own AI.

Thank you! Great feedback. Again agree with you on all points. Will take it onboard!

This is amazing. I agree with your take except "You’re not actually zeroizing the secrets"... I think it is actually calling zeroize() explicitly after use.

Can I get your review/roast on my approach with OrcaBot.com? DM me if I can incentivize you.. Code is available:

https://github.com/Hyper-Int/OrcaBot

enveil = encrypt-at-rest, decrypt-into-env-vars and hope the process doesn't look.

Orcabot = secrets never enter the LLM's process at all. The broker is a separate process that acts as a credential-injecting reverse proxy. The LLM's SDK thinks it's talking to localhost (the broker adds the real auth header and forwards to the real API). The secret crosses a process boundary that the LLM cannot reach.

Indeed. The biggest waste might be the overuse of MCP for everything. Sure it makes the initial development easier but then for every connection you're using a hundred billion dollar parameter model to decide how to make the call when it's usually completely unnecessary and then prone to random errors. MCP is the hammer that can make literally everything look like a nail...

As someone who has been waiting for the same thing as op tyre posted, I went to investigate this claim and it seems that it might be true but only when running apps within the Google AI Studio itself.. ie if you were to make an app that was on something like the App Store using Google AI Studio, it would be back to an API key that the developer bears the costs for.

The problem with the current model is that there is a high barrier to justifying the user pays essentially a 2nd/3rd subscription for ultimately the same AI intelligence layer. And so you cannot currently make an economically successful small use case app based on AI without somehow restricting users use of AI. I don't think AI companies are incentivized to fix this.

Hi Devin and other folks, I'm looking for software developers who are blind or hard of sight as there is a tool I'm building that I think might be of interest to them (it's free and open source). If you or anyone you know is interested in trying it please get in touch through my email.

Yeah that sounds reasonable. I've been thinking about how to make it more modular. I'll make it so that base TalkiTo doesn't need any heavy libraries.

EDIT: also to be clear whisper doesn't run or even download the model unless it's selected and the user confirms the DL. This can be configured. Google cloud has a free ASR option and ASR can be switched off completely.

You've hit the nail on the head of one of the main motivators of this project! I always context switch and miss when its done its task or sometimes forget completely..

So essentially at present when you setup TalkiTo with a Slack bot (instructions are shown by running `talkito --setup-slack`) it will do this its just its sending all the output to slack not just the final completion. I have verbosity levels and I could try tweaking them so that -verbosity 0 essentially does what you want ie filter everything except for prompts to the user. If you put in an issue on GitHub I'll get to it!

Right. On the whole I think these things are incredible.. looking to try myself after reading here in HN the other day about it working for all sorts of distractions. Just wanted to point out it's not all sunshine and rainbows which would certainly be suspicious.

There have been some. I've heard about eyesight related issues. A quick google found this article [0] where results showed that people using GLP-1 drugs were 68.6 times more likely to develop certain types of vision problems.

[0]: https://www.aao.org/newsroom/news-releases/detail/do-glp-1-d...

I tried pushing this 5 years ago when at Apple but got nowhere. IMHO only the OEM’s can achieve this.

Yes and this helps us make a start. It slightly increases the odds of life elsewhere. And yes there are other dangers.. climate change, nuclear armageddon, bio weapons etc but the existence of another problem doesn’t mean you shouldn’t also attempt to tackle this one. Specially as unlike the others a band aid seems somewhat tractable..

Researcher: “with this new device we think we can attempt to create a gravity wave in the lab” Professor: “we should consider whether this might violate the 2028 embargo on dark forest beacon technology”

You absolutely can make a local MCP server! I use one as part of TalkiTo which runs one in the background and connects it to Claude Code at runtime so it looks like this:

talkito: http://127.0.0.1:8000/sse (SSE)

https://github.com/robdmac/talkito/blob/main/talkito/mcp.py

Admittedly that's not as straight forward as one might hope.

Also regarding this point "letting you easily connect to your own Agents SDK MCP servers deployed in their cloud" I hear roocode has a cool new remote connect to your local machine so you can interact with roocode on your desktop from any browser.

Regardless of incentives I think this is some of the most important research they should be doing. As a species we need to get a better understanding of the probability of life on other planets and therefore a better understanding of fermi's paradox in case the dark forest theory is correct. So if NASA has an incentive to discover potential pathways for extraterrestrial life... great!

Agree. Out of the available paid cloud providers, I only chose to work with Claude Code because of the data privacy policy. This isn’t a welcome move but still usable. Thankfully the open source models are not far behind with Qwen 3 coder etc.

GosuCoder's latest video seems to be a well timed test of using Ryzen AI Max on some local models getting 40 TPS on a quantized Qwen 3 coder.

https://www.youtube.com/watch?v=0DET4YFzS6A

seems about right to me!

Thanks for the mention! Yeah I first wanted Claude Code to be more hands free when doing things around the house so added voice.. then I thought it would be great if we could go out and get messages read out by Siri on the AirPods when there is an update, and reply that way, so I added WhatsApp support specifically for this purpose. I'd be down for adding a phone option or Signal alternative but I'd be curious to know if the WhatsApp feature solves your problem? https://github.com/robdmac/talkito

Thank you! The SMS is feature is untested so I don't mention it much. I think unlike the others (TTS/ASR/Slack/Whatsapp) SMS will require a paid account on twilio. Twilio can’t absorb the carriers network costs for free like they can with WhatsApp sandboxing. If it's critical for you id be happy to work with you to get that feature working properly!

Also looking more closely at yours I notice the Apache 2.0 license but that doesn't prevent a company taking your work and running it as a SAAS which seems to be how you yourself want to monetize. For this reason I went with AGPL-3.0 so I recommend looking into that.

Like others (smithclay, sst/opencode) have said about aiming for a similar feature, I had plans to make a mobile app for Talkito[0][1] which primarily adds voice TTS/ASR and WhatsApp/slack interactions to Claude Code.

This looks like exactly what I was envisioning so congrats on getting out there first! LMK if you want to add voice controls to this.

[0]: https://github.com/robdmac/talkito

[1]: https://talkito.com

I think this and the Bob Bilby episode demonstrate that the show isn't afraid to critique screen time and the very platforms they rely on.

Talkito does indeed support all the popular TTS and ASR cloud providers so you can bring your own key. But even without a key, on Mac it can use the system default TTS and googles free ASR for input.

So whats the benefit? Well for Claude Code this wrapper effectively bridges those TTS/ASR systems and CC so the voice interface is now there (CC doesn't have one). It doesn't just rely on MCP either (although it does start an MCP server for configuring via prompting) but instead directly injects the ASR and directly reads out CC's output when on.

It is free and open source so folks can inspect it and check it's not doing anything nefarious, so that others can contribute if they should choose. And the license is what it is as that seems to be the advice on this forum if you want to make sure a company can't just make a paid service out of your work.

Alright you twisted my arm im in. Already did a couple AI centric projects. HMU let's do this. Personally I want a bazaar for AI. not sure I like the future being decided by the current crop of billionaires.

With these agentic coders you can have better conversations about the code. My favorite use case with CC is after a day coding I can ask it to for a thorough review of the changes, a file, or even the whole project.. setting it to work when I go off to bed and have it ranking issues and even proposing a fix for the most important ones. If you get the prompt right and enable permissions it can work for quite a long time independently.

Talkito (I posted the link further up) is open source and unlike Superwhisper it makes Claude Code talk back to you as well - which was the original aim to be able to multitask.

Sorry to hear that and whilst it wasn't my original goal to serve such a use case I wonder if being able to interact with Claude Code via voice will help you? On MacOS it uses free defaults for TTS and ASR but you can BYOK to other providors. https://github.com/robdmac/talkito

Looks like this was the other opencode[0] and got (sensibly) rebranded:

[0]: https://github.com/opencode-ai/opencode

Nice! This reminds me of my PhD research! I built some similar tools to go the other way (for comparing similarity with scores) but probably nowhere near as reliable as this. QQ How do you handle repeat segments? I remember having to extrapolate the x2's etc but in your you could detect patterns and do the reverse for compactness.

I'm working on an open source wrapper and MCP server to give Claude Code voice capabilities (and Slack and WhatsApp messaging). It works with system default TTS and google free ASR on Mac out the box but allows you to BYOK to your favorite TTS/ASR provider. I've also tried to make it a viable python library to make it easy to switch between ASR/TTS providers.

With Claude Code I really like being able to multi-task but right now it's a bit like a Tesla on autopilot needing your hands still on the wheel. With TalkiTo I can do housework/go out for lunch and keep it on the right track remotely.

https://github.com/robdmac/talkito