Many commentators are, mostly fairly, criticizing the repo due to issues raised on benchmarks. This is reasonable, however many are going further to bash the repo likely due to the authors.
For me, I see a silver lining. I'll be implementing mempalace for a few small agents to have memory portability that's managed locally.
I think the benchmarker who ran independent tests in GitHub issue #39 summed it up best:
To be clear about what this all means for our own use case: we still think there's a real product here, just not the one the README is selling. The combination of a one-command ChromaDB ingest pipeline for Claude Code, ChatGPT, and Slack exports, a working semantic search index over months or years of conversation history, fully local, MIT-licensed, no API key required, and a standalone temporal knowledge graph module (knowledge_graph.py) that could be used independently of the rest of the palace machinery,is genuinely useful, and we're planning to integrate it into our Sandcastle orchestrator as a claude_history_search MCP tool exactly along those lines.
Just use opus. A company that has not rejected agreements with a “Department of War” and sanctions reasoning models to enable mass citizen surveillance and autonomous weapons deployment with no human intervention is not really the kind of company I want to give my money too. And opus4.6 is the best model out there. Some people overthink on personality but I just want good code.
CLI is a clear choice (right now) for terse, individual use cases, but we need to remember - MCP is a protocol and a new one.
If we think back, even HTTP needed a decade to stabilize and dominate the other early web protocols. Before we throw out MCP, we'll have to see how important stateful vs stateless is for agents. It is still early days of real-world development!
Not knowing the scene and only what I took from the article - it’s precisely this. There is a reverence towards human labour and effort that affords relaxing what are generally accepted social contracts in other areas (e.g. copying). It’s a very interesting social construct where the self-policing is in a very specific are whilst other areas are forgiven.
If we fully embrace this generative software concept for the sake of this thread, then the UI/UX, is going to be optimized and personalized to your tastes, skills, affinities, and (dis)abilities. Brand comes into the equation as a proxy for trust, so if this whole scenario were to come true, maybe that's not so relevant anymore.
Do you have plans to port your proprietary library MetalRT to mobile devices? These performance gains would be a boon for privacy-centric mobile applications.
Yes, mobile is our primary offering and it is on the roadmap. The same Metal GPU pipeline that powers MetalRT on macOS maps directly to iOS (same Apple Silicon,
same Metal API)
I don’t agree that it’s a nitpick - it’s a fundamental communication tool to users that describes capabilities and costs. Versioning is not the problem, but it amplifies the mess.
To be more direct on the point: Anthropic has nailed that Opus > Sonnet > Haiku.
> To be more direct on the point: Anthropic has nailed that Opus > Sonnet > Haiku.
Holy cow I never realized and I had to keep checking which model was which, I never had managed to remember which model was which size before because I never realized there was a theme with the names!
I assume 5.4 is just the latest version. So if I'm on 5.1, I need to plan to upgrade to the latest version. I may assume the pricing is roughly the same, as well as the speed, and the purpose.
If I'm on Haiku, I don't assume I need to upgrade to Opus soon. I use Haiku for fast low reasoning, and Opus for slower more thoughtful answers.
And if I'm on Sonnet 4.5 and I see Sonnet 4.6 is coming out, I can reasonably assume it's more of a drop in upgrade, rather than a different beast.
People are building for themselves. However I’d also reference www.Every.to
They built the popular compound-engineering plugin and have shipped a set of production grade consumer apps. They offer a monthly subscription and keep adding to that subscription by shipping more tools.
My iPad Pro must by the model ahead of yours. I just upgraded the OS to v26 and it’s awful - sluggish, jittery, inconsistent typing experience - borderline unusable for a fast work environment. With no downgrade option I’m forced to buy a new one for work and relegate the older device to entertainment or kids use only.
Being stuck on v17 is a feature for the older A-series chipset.
I'm in the same boat. Thankfully, I only use my iPad for watching videos while I'm cooking, but if were using it for anything else, I'd have to replace it.
For me, I see a silver lining. I'll be implementing mempalace for a few small agents to have memory portability that's managed locally.
I think the benchmarker who ran independent tests in GitHub issue #39 summed it up best:
To be clear about what this all means for our own use case: we still think there's a real product here, just not the one the README is selling. The combination of a one-command ChromaDB ingest pipeline for Claude Code, ChatGPT, and Slack exports, a working semantic search index over months or years of conversation history, fully local, MIT-licensed, no API key required, and a standalone temporal knowledge graph module (knowledge_graph.py) that could be used independently of the rest of the palace machinery,is genuinely useful, and we're planning to integrate it into our Sandcastle orchestrator as a claude_history_search MCP tool exactly along those lines.
https://github.com/milla-jovovich/mempalace/issues/39
reply