vault81/redvault-ai
4
0
Fork 0
Code Issues 1 Pull requests 1 Projects 1 Releases Packages Wiki Activity
No description
10 commits 2 branches 0 tags 5.3 MiB
Rust 68.9%
Emacs Lisp 17.6%
Nix 5.5%
TypeScript 2.8%
SCSS 2.1%
Other 3.1%
Find a file
Tristan Druyen 034895d7d4
Update main README.md
2024-10-08 17:33:43 +02:00
.nix WIP 2024-09-05 22:33:13 +02:00
docstub WIP 2024-09-05 22:33:13 +02:00
frozen_llama Remove iced dir & add as git dep 2024-09-09 11:46:22 +02:00
leptos_stub Remove unused pkg 2024-09-09 15:49:41 +02:00
llama_forge_rs Remove unused pkg 2024-09-09 15:49:41 +02:00
llama_proxy_man Fix warning 2024-10-08 17:29:43 +02:00
.envrc Init 2024-07-21 02:42:48 +02:00
.gitignore WIP 2024-09-05 22:33:13 +02:00
Cargo.lock Optimize by stopping large models first 2024-10-08 17:29:11 +02:00
Cargo.toml Add llama_proxy_man pkg 2024-09-19 17:21:46 +02:00
clippy.yml Remove unused pkg 2024-09-09 15:49:41 +02:00
flake.lock Optimize by stopping large models first 2024-10-08 17:29:11 +02:00
flake.nix Optimize by stopping large models first 2024-10-08 17:29:11 +02:00
package-lock.json Init 2024-07-21 02:42:48 +02:00
package.json Init 2024-07-21 02:42:48 +02:00
README.md Update main README.md 2024-10-08 17:33:43 +02:00
rust-toolchain.toml WIP 2024-09-05 22:33:13 +02:00

README.md

Redvau.lt AI Monorepo

Current Repos

  • llama-forge-rs old alpha-state webview based GUI app for chatting with ai, manages a llama-server in the background
  • llama-proxy-man proxy which auto starts/stops llama.cpp instances, while retring requests and keeping the connection open so you can run more models than your VRAM can fit, with all api requests working (they'll just be slow if you have to start instances to make them happen)

Ideas

  • emacs-qwen-plugin
    • use emacs-module-rs + llama.cpp/proxy to get awesome qwen integration into emacs
  • agent
    • add experimental rag+agent framework