#99 · Primary category： Inference & Local Deploy
Atomic-Chat
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
Project last updated：08/28/26
GitHub Stars
1.4K
Forks
160
Contributors
176
License
Other
Why we included this project
If your work involves running open-weight models on your own hardware, this is one of the more complete entry points you'll find. Atomic Chat bundles three inference backends behind a single OpenAI-compatible server on localhost:1337: its own llama.cpp fork with KV-cache optimizations, upstream llama.cpp, and an Apple Silicon MLX-VLM engine. A coding agent, CLI tool, or IDE plugin that already speaks the OpenAI API can point at your local models without extra glue code, and speculative decoding features like MTP and DFlash speed up generation on supported models. The desktop app also handles model downloads from Hugging Face, offers a chat UI, supports MCP servers, and lets you mix local and cloud providers per chat. The loopback-only server and bring-your-own-key setup are what make it work for teams that want to keep conversations on their machine while still feeding their favorite agent tools.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.