GitHub - KishaWeb/local-char: an locall ai software that you can give your llm commands to act like your wanted character. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
KishaWeb
local-char
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>23 Commits<br>23 Commits
src
src
.gitignore
.gitignore
Cargo.lock
Cargo.lock
Cargo.toml
Cargo.toml
LICENSE
LICENSE
README.md
README.md
history.json
history.json
history_tui.json
history_tui.json
history_web.json
history_web.json
View all files
Repository files navigation
local char
local char is a cli and a web program that runs ai locally that can act like the character you want, the characters are mostly mad for 3-5 b models not very strong im going to add different category for the range strength of each model so it can act better like your desired character, and you dont need any cloud service, no accounts and no subscriptions.
features
locally run ai with llama.cpp
has a cli
currently have 24 characters
chat history
made for weaker models (for now)
chat history
great tui (terminal ui)
really basic web server (with character selecting)
lan sharing
pinning and deleting chats
Lightweight and fast
works well on smaller models
requirements
Rust<br>-llama.cpp
a GGUF model
setup
This project expects llama.cpp running .
You need to start llama.cpp in server mode so it exposes an API endpoint:
how to start:
git clone https://github.com/ggml-org/llama.cpp.git<br>cd llama.cpp<br>./build/bin/llama-server -m PATH-TO-YOUR-MODEL.gguf
install
make sure llama.cpp server is running
git clone https://github.com/KishaWeb/local-char.git<br>cd local-char<br>cargo install --path .<br>local-char
usage
local-char tui (runs tui)<br>local-char web [--lan] (starts the web server, if you use --lan it enables lan sharing)
if your running it in cargo use it like this:
cargo run -- tui (runs tui)<br>cargo run -- web (starts web server, if you use --lan it enables lan sharing)
current roster includes characters from
Serial Experiments Lain
Steins;Gate
The Boys
Death Note
Code Geass
Berserk
NieR
Persona
Attack on Titan
frieren
Neon Genesis Evangelion
ghost in the shell
gurren lagann
Philosophy
local char focuses on:
locally running models
being simple
character roleplay
license
MIT
About
an locall ai software that you can give your llm commands to act like your wanted character.
Resources
Readme
License
MIT license
Uh oh!
There was an error while loading. Please reload this page.
Activity
Stars
star
Watchers
watching
Forks
forks
Report repository
Releases
No releases published
Packages
Uh oh!
There was an error while loading. Please reload this page.
Contributors
Uh oh!
There was an error while loading. Please reload this page.
Languages
Rust<br>66.2%
JavaScript<br>17.6%
CSS<br>12.2%
HTML<br>4.0%
You can’t perform that action at this time.