-
If you gravitate to GitHub Copilot Chat but want more model choice, codecompanion.nvim is for you. It opens a resizable floating panel where you can talk to Anthropic Claude, Google Gemini, Ollama, or plain OpenAI. Inline edits (“fix this function” or “add unit tests”) are just a visual-mode mapping away, and every conversation gets stored so you can scroll back for context.
-
Stream
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video. Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
-
model.nvim is a Swiss-army knife for LLMs. Instead of binding to one provider, it exposes a prompt-builder API you script in Lua. Switch from GPT-4 to a local Llama-2 quantization with a single config line, or combine multiple providers in one workflow. Ideal for privacy-sensitive or budget-conscious teams.
-
Part of the Dense Analysis ecosystem, neural delivers inline GPT suggestions with near-zero configuration. Highlight code, run :Neural rewrite optimize, and watch a side buffer populate with an optimized version. Because it’s built by the maintainers of ALE, it fits naturally alongside lint diagnostics and code actions.
-
GPTModels.nvim
GPTModels - a multi model, window based LLM AI plugin for neovim, with an emphasis on stability and clean code
GPTModels.nvim opts for a multi-window interface: chat in one split, reference docs in another, and your code remains full-width. The key selling point is stability; the author focuses on graceful error handling and connection retries so your Insert-mode never freezes waiting on the network.
-
If you use Neovim and haven’t tried nvim-cmp, start here. It’s the de-facto completion framework, written in Lua, feeding on LSP, path, buffer, snippet, and AI sources. Everything in the popup—icons, ghost text, documentation windows—is customizable, and its community drives dozens of extension sources.
-
Proof assistants are niche—but if you study Lean, lean.nvim feels magical. It shows goal states in virtual text, recommends tactics, and even auto-formats proofs. The plugin single-handedly makes Neovim a serious alternative to VS Code in the formal-methods space.
-
Wrangling a 2-MB JSON file? nvim-jqx opens a sidebar where you run jq filters, explore nodes, and push results back into your buffer. No more piping through command-line jq and losing your place.
-
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
-
ray-x/go.nvim
-
Testing in Go lives on table-driven patterns. gotests.nvim wraps the popular gotests CLI, letting you generate tests for the function under cursor with a single command. It even respects build tags and vendor directories.