codecompanion.nvim

I used mcp-neovim-server to let my LLM control my vim session. that way it can debug and test and poke around. It's crazy good at debugging plugins. It's absurd how little these things need to look-up docs; half these models are just out the box wildly good at vim. "Open these files on these lines" and now there are four splits with me at the relevant line numbers. Awesome. And it'll explain how to do things & test it out & validate! https://github.com/bigcodegen/mcp-neovim-server That was a little tricky to set-up. I ended up writing nvim-auto-listen, which uses some heuristics to find your project root, and starts a .nvim.socket in that directory. That makes it easy for mcp-neovim-server instances to find. https://github.com/rektide/nvim-auto-listen/ I'm only somewhat getting started, but the workmanship, fit and finish is just outstan

This doesn’t even come close to CodeCompanion[1], which doesn’t require any new LSP config/dependencies or filetype limitations. There is no ability to share the current buffer(s) for context, no tool support. This seems like a checkbox release. You’re better off using CodeCompanion with Amazon Bedrock, which includes the added benefit of sovereignty. [1]: https://github.com/olimorris/codecompanion.nvim

I'm curious if this was created for/by Zed (which recently added support for it [0]) or if it was pioneered by the Neovim plugin [1] and caught the Zed team's attention? The plugin doesn't seem to have any ties to the Zed editor that I can see, and hopefully if this was the product of discussions among different participants in the space it'll pick up steam quickly. [0] https://zed.dev/releases/stable/0.201.4 [1] https://github.com/olimorris/codecompanion.nvim

Have you seen CodeCompanion (https://github.com/olimorris/codecompanion.nvim)?

I've used it a ton too and it feels quite polished. Lately I've seen codecompanion.nvim[1] around a lot and been wondering if someone has tried both, are there differences between these two in actual use that would make other one worth trying over the another? [1] https://github.com/olimorris/codecompanion.nvim

Yes, copilot's tab in vim is that made me think that AI is useless. However next iteration of AI coding tools made me rethink this (I am using https://github.com/olimorris/codecompanion.nvim with nvim now).

this plugin is designed specifically for the llama.cpp server api, if you want copilot like features with ollama, you can use an ollama instance as a drop-in replacement for github copilot with this plugin: https://github.com/bernardo-bruning/ollama-copilot There is also https://github.com/olimorris/codecompanion.nvim which doesn't have text completion, but supports a lot of other AI editor workflows that I believe are inspired by Zed and supports ollama out of the box

Not vim, but neovim: https://github.com/olimorris/codecompanion.nvim Haven't used it yet but it supports many models.

llama3.3:70b-instruct-q4_K_M (~43 GB, 2x 3090/4090 or fast memory cpu inference on e.g. macs) or qwen2.5-coder:32b-instruct-q5_K_M (~23 GB) or gemma2:9b-instruct-q6_K (~7.5 GB) and https://github.com/bernardo-bruning/ollama-copilot or alternatively: https://github.com/ollama/ollama + https://github.com/olimorris/codecompanion.nvim

- https://github.com/olimorris/codecompanion.nvim - https://github.com/yetone/avante.nvim Did not have the time to test them yet and there are probably more.

Another one.. https://github.com/olimorris/codecompanion.nvim

If I just use nvim and my own AI plugin ecosystem, is Zed AI worth trying? https://github.com/jackMort/ChatGPT.nvim https://github.com/olimorris/codecompanion.nvim https://github.com/Robitx/gp.nvim https://github.com/frankroeder/parrot.nvim