Home / Open source / omlx
omlx
MCP mentionedjundot/omlx · Enterprise stack · Enterprise
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Verified via GitHub API
- apple-silicon
- inference-server
- llm
- macos
- mlx
- openai-api
Data from GitHub API, refreshed Oct 17, 2026
- Stars
- 22878
- Forks
- 2072
- License
- Apache-2.0
- Language
- Python
- Last commit
- Oct 17, 2026
- Latest release
- v0.7.1rc1
- Release date
- Oct 15, 2026
- Contributors
- 325
- Open issues
- 390
Works with — from README
- MCP
- MCP mentioned
- Models
- Claude, DeepSeek, Llama, Mistral, OpenAI, Qwen
Source: README.md keyword match (stated in README)
omlx FAQ
Is omlx free?
omlx is open source under the Apache-2.0 license. Hosted services and infrastructure may have separate costs.
How popular is omlx?
omlx has 22878 GitHub stars as of Oct 17, 2026.
Is there a hosted version of omlx?
A hosted alternative for omlx is unknown (—) in this data.
What does omlx work with?
From README: MCP mentioned, Claude, DeepSeek, Llama, Mistral, OpenAI, Qwen.