← Open Source
psugihara

FreeChat

llama.cpp based AI chat app for macOS.

ApplicationsPersonalSwift
Open on GitHub
Momentum
+0stars in 24 hours0.0%
503
Stars
43
Forks
+0
This week
4
Contributors
Created 2023-08-04 · Updated 2026-09-23 · #18264 today
Top developers
psugiharashavitverhovsky

psugihara/FreeChat is ranked 18,264 with 503 stars.

Same-category comparison

psugihara/FreeChat is ranked 18,264 among these 8 peers; noho/dayu-agent is ranked 18,263.

Same-category comparison
NameRankMetrics
adewaskar/jarvis18,229
Language:
TypeScript
Stars:
504
Forks:
218
Description:
J.A.R.V.I.S for automating your daily tasks using Claude Code.
deonmenezes/mantishack18,256
Language:
Rust
Stars:
503
Forks:
76
Description:
Mantis Hack.
jasonjmcghee/plock18,260
Language:
Rust
Stars:
503
Forks:
32
Description:
From anywhere you can type, query and stream the output of any script (e.g. an LLM).
noho/dayu-agent18,263
Language:
Python
Stars:
503
Forks:
136
sadjow/claude-code-nix18,266
Language:
Shell
Stars:
503
Forks:
36
Description:
Always up-to-date Nix package for Claude Code with hourly updates from Anthropic's native releases.
ynagatomo/ImgGenSD218,272
Language:
Swift
Stars:
503
Forks:
57
Description:
An iOS app that generates images using Stable Diffusion v2.
DrewNF/Tensorflow_Object_Tracking_Video18,273
Language:
Python
Stars:
502
Forks:
195
Description:
Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition.
andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-18,281
Language:
HTML
Stars:
502
Forks:
105
Description:
Claude Cowork plugin for job seekers. 9 AI skills: evaluate job postings, generate ATS-optimized resumes, scan company career portals, track applications, draft outreach. Works in any industry.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageSwift
CategoryApplications
SubcategoryPersonal
KeywordsAI character, LocalAI, Memory management
Stars503
Forks43
Contributors4
Created date2023-08-04
Updated date2026-09-23
Stars in 1 day0
Stars in 7 days0
Rank18,264
Previous rank18,019
Rank change-245
7-day stars rank16,562
Previous 7-day stars rank16,580
7-day stars rank change18
Total stars rank19,286
Previous total stars rank19,263
Total stars rank change-23
CountryUSA
README summary

FreeChat Chat with LLMs on your Mac without installing any other software. Every conversation is saved locally, all conversations happen offline. Customize persona and expertise by changing the system prompt Try any llama. cpp compatible model No internet connection required, all local (with the option to connect to a remote model) Install Join the TestFlight beta: Or download on the Mac App Store: Or build from source via "Archive" in Xcode after completing dev setup below. Goals The main goal

of FreeChat is to make open, local, private models accessible to more people. FreeChat is a native LLM appliance for macOS that runs completely locally. Download it and ask your LLM a question without doing any configuration. A local/llama version of OpenAI's chat without login or tracking. You should be able to install from the Mac App Store and use it immediatly. Usable by people who haven't heard of models, prompts, or LLMs. Performance and simplicity over dev experience

or features. Core functionality should not require an internet connection. Talk about whatever you want with FreeChat, just like Notes. What's the point of running local AI if you can't audit that it's actually running locally? Upgrade your models Once you're up and running, it's fun to try different models in FreeChat. The AI training community is releasing new models basically every day. FreeChat is compatible with any gguf formatted model that llama. Models are usually named with their parameter

count (e. 7B) and are formatted with different levels of lossy compression applied (quantization). The general rule of thumb is that models with more parameters tend to be slower and wiser and more quantization makes it dumber. Most models have a linked "model card" by the author that discusses its training and abilities. cpp compatible model [x] Change system prompts to modify personas or expertise [x] Download models from within the app (shrink app from 3GB to 10mb, way better

for updates) [x] Advanced settings (prompt format, temperature, repeat penalty) [ ] Personas - save system prompt / model settings for later and change personas when you create a new conversation [ ] Search conversations Contributing Contributions are very welcome. Let's make FreeChat simple and powerful. Credits This project would not be possible without the hard work of: Georgi Gerganov for llama. cpp Meta for training Llama 2 Jon Durbin for training Spicyboros, the default model TheBloke (Tom Jobbins) for model quantization Monica Kogler for the

FreeChat logo and uncountable UX consults Also many thanks to Billy Rennekamp, Elliot Hursh, Tomás Savigliano, Judd Schoenholtz, Alex Farrill for invaluable spitballing sessions.

Frequently asked questions

How many stars and forks are recorded?

psugihara/FreeChat has 503 stars and 43 forks.

What is the repository rank?

psugihara/FreeChat is ranked 18,264.

What language and category are recorded?

psugihara/FreeChat has 503 stars, uses Swift and belongs to Applications.

Which repository is closest in rank?

psugihara/FreeChat is compared with noho/dayu-agent, ranked 18,263 with 503 stars.

README

FreeChat

Chat with LLMs on your Mac without installing any other software. Every conversation is saved locally, all conversations happen offline.

  • Customize persona and expertise by changing the system prompt
  • Try any llama.cpp compatible model
  • No internet connection required, all local (with the option to connect to a remote model)

https://github.com/psugihara/FreeChat/assets/282016/fd546e39-7657-4ccd-a44f-0b872547a629

Install

Join the TestFlight beta: https://6032904148827.gumroad.com/l/freechat-beta

Or download on the Mac App Store: https://apps.apple.com/us/app/freechat/id6458534902

Or build from source via "Archive" in Xcode after completing dev setup below.

Goals

The main goal of FreeChat is to make open, local, private models accessible to more people.

FreeChat is a native LLM appliance for macOS that runs completely locally. Download it and ask your LLM a question without doing any configuration. A local/llama version of OpenAI's chat without login or tracking. You should be able to install from the Mac App Store and use it immediatly.

  • No config. Usable by people who haven't heard of models, prompts, or LLMs.
  • Performance and simplicity over dev experience or features. Notes not Word, Swift not Elektron.
  • Local first. Core functionality should not require an internet connection.
  • No conversation tracking. Talk about whatever you want with FreeChat, just like Notes.
  • Open source. What's the point of running local AI if you can't audit that it's actually running locally?

Upgrade your models

Once you're up and running, it's fun to try different models in FreeChat. The AI training community is releasing new models basically every day. FreeChat is compatible with any gguf formatted model that llama.cpp works with.

Models are usually named with their parameter count (e.g. 7B) and are formatted with different levels of lossy compression applied (quantization). The general rule of thumb is that models with more parameters tend to be slower and wiser and more quantization makes it dumber.

To find models, try Hugging Face. Most models have a linked "model card" by the author that discusses its training and abilities.

Dev Setup

  1. Open mac/FreeChat.xcodeproj
  2. Run and fix errors

Roadmap / TODO (roughly in order):

  • [x] Chat with Llama 3 without installing anything else
  • [x] Try any llama.cpp compatible model
  • [x] Change system prompts to modify personas or expertise
  • [x] Download models from within the app (shrink app from 3GB to 10mb, way better for updates)
  • [x] Advanced settings (prompt format, temperature, repeat penalty)
  • [ ] Personas - save system prompt / model settings for later and change personas when you create a new conversation
  • [ ] Search conversations

Contributing

Contributions are very welcome. Let's make FreeChat simple and powerful.

Credits

This project would not be possible without the hard work of:

  • Georgi Gerganov for llama.cpp
  • Meta for training Llama 2
  • Jon Durbin for training Spicyboros, the default model
  • TheBloke (Tom Jobbins) for model quantization
  • Monica Kogler for the FreeChat logo and uncountable UX consults

Also many thanks to Billy Rennekamp, Elliot Hursh, Tomás Savigliano, Judd Schoenholtz, Alex Farrill for invaluable spitballing sessions.

Nearby in the ranking
Similar items