Has anyone checked out the new Cline updates?

Just played with this yestereday!

But has anyone checked out the updates to Cline (VS Code Plugin) recently, with GitHub Codespaces? It’s pretty cool, I’m just not a big fan having to re-start them when they go idle.

It’s similar to Bolt.diy but allows for integration of tools through MCP’s which is pretty awesome. But unlike bolt, it’s a bit heavier and can’t run in Cloudflare Pages… it basically requires a dedicated Cloud VM instance. And sadly, the 'Cline (prev. Claude Dev)' extension is not available in Code for the Web. Learn Why.

We need like all of these features, and RAG integration like AnythingLLM.

And it uses credits like crazy as it’s system prompt is absurdly long. And this makes it work horribly with Ollama/LMStudio. I had issues with getting local models through Ollama/LMStudio working with GitHub Codespaces. I kind of ran into a catch 22. MCP’s worked well through the GitHub Codespace, but no locally (still not sure why, need to troubleshoot further; likely mixed content and/or security related). But while MCP’s worked in the Codespace, local models would not (without some DNS trickery through a Cloudflare Proxy). And even then the response was very slow and the system prompt is definitely not designed for other models. I often got errors that the model (even set to 8,000 max tokens) did not have enough tokens to process the request (had to bump this to 16,384).

I think we could use a reasoning model (QwQ to dynamically build contextually aware system prompts, concise to the thing you are trying to solve with the “cheap” model and probably reduce initial token usage by like 75% and get better responses).

Just thought this was pretty cool!

1 Like

I have been using Cline for a couple of months now and I have been impressed overall. With it, I have nearly completed a Vue web application with a PostGres database. Previously, I had tried both GitHub CoPilot and Cursor, but I found that Cline used with Claude 3.5 Sonnet within VS Code was a superior coder and its context awareness was generally quite good, especially if I specified the files needed to consider for each request.

That said, I have been somewhat displeased with the way that it burns through my Anthropic credits/tokens.

I am not sure what you mean by “…having to re-start them when they go idle”, but I think you are talking about clicking on one of the “Recent Tasks” to reopen and I assume to somewhat hydrate the context. Is this what you mean? If so, I found it a little obtuse at first, but now I like having that history and being able to go back and reopen one if needed. In all fairness, I am not really sure how other applications are using this.

For now, I am mainly interested in building web apps and b2b saas apps. I am very interested to know what AI tool you would recommend for these jobs. I have been considering giving bolt a try, but I really dislike hopping back and forth and I would prefer to learn a single tool that will hopefully continue to remain relevant (and solvent if applicable) and stick with it moving forward. Nevertheless, with all of this being so fluid right now, it is difficult to make an assessment with a high degree of certainty. That is my opinion, though, and again, I would love to know your thoughts.

2 Likes

this looks nice.

yes definitely

2 Likes