Hacker News Reader

Cline or Roo Cline allows for local LLMs to be used. OpenRouter.ai - has made both Google Gemini 2.0 flash and thinking free!

You could try OpenHands + OpenRouter + Llama (https://docs.all-hands.dev/modules/usage/llms/openrouter) I haven't tried it and don't know how it would go.

Llama.vscode and llama.vim look promising.

continue.dev, aider, Zed’s AI assistant are all free and will work with a local Ollama installation.

You will of course need an insanely beefy and expensive machine to run any useful models at reasonable speeds, which would likely cover API usage costs for many, many years (an entire lifetime, likely).

Unless you want to fine tune your custom model and/or have strict on prem requirements… shit gets expensive fast, but it’s probably worth it for some

Cline also supposedly supports Ollama but it doesn't work that well with most models. There are some models dedicated to cline.

That’s a google away. It’ll be noticeably inferior to the hosted frontier models though

CodeGPT for idea platform