Skip to content

The Stacks

Wing of Apps

End-user AI applications you can run or self-host.

Free to explore · curated by OneWave AI

315 apps projects in this wing of the Stacks. Review status is shown for every entry.

AI searches are sent to OpenAI.

Review is in progress. 1,407 projects are queued and none has been approved yet. Everything unreviewed is discovery metadata imported from GitHub — listed, not vetted.

Request a review · What we check

Ranked by total stars at the last daily refresh. This is not stars earned during the selected period. Star counts in the AI category are known to be inflated by fake-star campaigns, so activity and license are shown first.

9 projects matching “inference”
hpcaitech organisation mark

ColossalAI

hpcaitech/ColossalAI

Making large AI models cheaper, faster and more accessible

Pushed yesterday.Apache License 2.0PythonApps41.4k
2noise organisation mark

ChatTTS

2noise/ChatTTSSlowing

A generative speech model for daily dialogue.

Last push 7 months ago.GNU Affero General Public License v3.0PythonApps40.0k+16
chatchat-space organisation mark

Langchain-Chatchat

chatchat-space/Langchain-ChatchatDormant

Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

No push in over a year ago.Apache License 2.0PythonApps38.7k
gitleaks organisation mark

gitleaks

gitleaks/gitleaks

Find secrets with Gitleaks 🔑

Pushed 16 days ago.MIT LicenseGoApps31.0k+270
mozilla-ai organisation mark

llamafile

mozilla-ai/llamafile

Distribute and run LLMs with a single file.

Pushed 4 days ago.OtherC++Apps26.6k+57
Lightning-AI organisation mark

litgpt

Lightning-AI/litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Pushed 2 days ago.Apache License 2.0PythonApps13.7k
mw00 organisation mark

project-maya

mw00/project-maya

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

Pushed yesterday.MIT LicenseC++Apps2.8k
youssofal organisation mark

MTPLX

youssofal/MTPLX

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Pushed 6 days ago.Apache License 2.0PythonApps2.7k+25
microsoft organisation mark

foundry-local

microsoft/foundry-local

No description provided by the repository owner.

Pushed today.OtherC++Apps2.6k+41
Apps — open-source AI apps — Techandria