https://github.com/okuvshynov/vimqq
local LLM chat for vim with dynamic warmup, forks and multi-model support
https://github.com/okuvshynov/vimqq
llm vim
Last synced: 3 months ago
JSON representation
local LLM chat for vim with dynamic warmup, forks and multi-model support
- Host: GitHub
- URL: https://github.com/okuvshynov/vimqq
- Owner: okuvshynov
- License: mit
- Created: 2024-06-25T19:39:37.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-01-16T20:43:26.000Z (over 1 year ago)
- Last Synced: 2025-01-16T21:41:58.003Z (over 1 year ago)
- Topics: llm, vim
- Language: Vim Script
- Homepage:
- Size: 635 KB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Vim quick question (vim-qq)
**Undergoing major experimental changes for now**
AI plugin for Vim/NeoVim with focus on local evaluation, flexible context and aggressive cache warmup to hide latency.
https://github.com/user-attachments/assets/f1b34385-c6e2-4202-a17d-2ef09e83becc
Features (including experimental)
* Support for both remote models through paid APIs (Claude, Gemini) and local models via llama.cpp server;
* automated KV cache warmup for local model evaluation;
* dynamic warmup on typing - in case of long questions, it is a good idea to prefill cache for the question itself;
* human-readable hierarchical project indexing;
* llm agents in different roles: engineer, reviewer, etc.
* fully closing the loop and implementing complex features E2E