I wonder why doesnt it use RAG for code context retrival across the codebase? Is there some fundamental reason why init in for example claude coder makes this stupid claude.md file instead of vectorizing and indexing the codebase locally?
Show HN: Fork of Claude-code working with local and other LLM providers
31–40 of 41 posts
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#32I wonder why doesnt it use RAG for code context retrival across the codebase? Is there some fundamental reason why init in for example claude coder makes this stupid claude.md file instead of vectorizing and indexing the codebase locally?
The fundamental reason is that RAG kind of sucks and requires a ton of effort/optimization to reach a high degree of reliability for most applications. RAG solutions are not Anthropic's core product. Just reading all the relevant files is more expensive but is more effective and efficient from a dev time perspective.
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#33I guess the whole point of Claude Code was to show which prompts work the best and what stuff they fine-tune on
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#34How can it be a fork of Claude-code when it’s not open source?
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#35Earlier quoted context omitted.
Are there examples of LLMs fixing spaghetti code in the wild?
If your spaghetti code is written in React, Claude Code might be able to do it given enough time, and at the cost of a few million tokens.
Are there examples of non-spaghetti react out in the wild?
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#36Maybe it's easier to just set up a proxy mirroring Anthropic's API, but pointing to whatever model you want? Genuine doubt.
It's not much different than your proxy idea. It's implemented as a transformation between the internal message structure (close to Anthropic API's) to OpenAI message spec and vice-versa. Then, it's calling all the other models using the openai-node client, as pretty much everyone supports that now (openrouter, ollama, etc)
Cool! The only downside would be keeping your code in sync with upstream, then.
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#37Thanks a lot! Just wanted to say that for me, no Chromium install is complete without Little Rat there.
Very handy, thanks again for that.
For those who want to check it out, it's an extension to monitor/block network access of other extensions, it also lets you turn them on/off from the same screen:
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#38Thanks a lot! Just wanted to say that for me, no Chromium install is complete without Little Rat there. Very handy, thanks again for that. For those who want to check it out, it's an extension to monitor/block network access of other extensions, it also lets you turn them on/off from the same screen: https://github.com/dnakov/little-rat
Thanks! Love to hear people are still using it, even though it needs a flag toggle now.
Re: Show HN: Fork of Claude-code working with local and other LLM providers
#39Re: Show HN: Fork of Claude-code working with local and other LLM providers
#40I wonder why doesnt it use RAG for code context retrival across the codebase? Is there some fundamental reason why init in for example claude coder makes this stupid claude.md file instead of vectorizing and indexing the codebase locally?
Why spend Anthropic developer time on charging you less when an MVP impl can charge you $1 for indexing a simple small Helm chart?