Paged SSD KV caching
Stores KV cache blocks in safetensors format, keeping hot blocks in RAM and moving colder blocks to SSD with an LRU policy. Cached prefixes can be restored across requests and server restarts.
oMLX
Freemium
oMLX is a native macOS LLM inference server built on MLX for running compatible language, vision-language, embedding, and reranker models locally on Apple Silicon. Designed for coding-agent workflows, it works with Claude Code, OpenClaw, Cursor, and OpenAI-compatible clients.
What is oMLX?
oMLX is a native macOS inference server built on MLX for running MLX-format AI models locally on Apple Silicon. It provides a dashboard for managing models, chatting with them, and monitoring server metrics, while supporting LLM, vision-language, embedding, and reranker models.
The product is designed especially for coding-agent sessions in which the conversation context changes repeatedly. Its paged SSD KV cache can preserve cache blocks across requests and server restarts, reducing the need to recompute previously seen prefixes.
What can oMLX do?
Continuous batching
Uses mlx-lm’s BatchGenerator to handle concurrent requests instead of processing every request strictly one at a time. The site reports up to a 4.14× generation speedup at eight-way concurrency in its published benchmark.
Multi-model serving
Loads LLM, vision-language, embedding, and reranker models simultaneously, with LRU eviction available when memory runs low. Models can be browsed and downloaded from the administration dashboard.
OpenAI and Anthropic-compatible APIs
Provides `/v1/chat/completions` and `/v1/messages` endpoints for compatible clients, including Claude Code, OpenClaw, Cursor, and other OpenAI-compatible applications.
macOS administration app
The native menu bar app can start, stop, and monitor the server. Its web dashboard includes model management, chat, and real-time metrics; the app is signed, notarized, and includes in-app auto-update.
Tool calling and MCP
Supports JSON, Qwen, Gemma, GLM, and MiniMax tool-calling formats, plus MCP tool integration and configurable trimming of oversized tool results on a per-model basis.
Use Cases
“Local coding agents”
Use oMLX as a local backend for Claude Code, OpenClaw, or Cursor when an agent repeatedly revisits or changes context during a coding session.
“Concurrent local inference”
Serve multiple requests through continuous batching when several local clients or workflows need model generation at the same time.
“Model experimentation on Mac”
Manage and test MLX-format models from Hugging Face through the dashboard, including language, vision-language, embedding, and reranker models.
“Tool-enabled model workflows”
Connect models to applications that use tool calling or MCP, with support for several model-specific tool formats and optional tool-result trimming.
Frequently Asked Questions
What hardware and operating system does oMLX require?
oMLX requires an Apple Silicon Mac, from M1 onward, running macOS 15 or later. The site lists 16GB of RAM as the minimum and recommends 64GB or more for comfortable use with larger models.
Does oMLX work with Claude Code, OpenClaw, and Cursor?
Yes. It provides OpenAI-compatible `/v1/chat/completions` and Anthropic-compatible `/v1/messages` endpoints. Its dashboard can generate configuration commands for the supported tools.
Do existing models need to be downloaded again?
Not necessarily. oMLX can read the standard Hugging Face cache, an LM Studio folder, and custom directories. The dashboard also includes a Hugging Face downloader for new models.
Which models can oMLX serve?
The site states that oMLX supports MLX-format models from Hugging Face, including Qwen, LLaMA, Mistral, Gemma, DeepSeek, MiniMax, and GLM. Vision-language models are supported, and reasoning-model handling includes automatic `<think>` tag support.
How can oMLX be installed?
Users can download the macOS DMG or install from source. The source workflow requires Python 3.10 or later and Apple Silicon; the documented server example connects to compatible clients on localhost:8000.
Quick Facts
- Category
- Local AI inference server
- Platform
- macOS 15+ on Apple Silicon
- Model format
- MLX-format models from Hugging Face
- API compatibility
- OpenAI-compatible and Anthropic-compatible endpoints
- Primary workflows
- Coding agents, local model serving, and tool-enabled applications
- License
- Apache 2.0
oMLX Traffic Analysis
Traffic data is for reference only.
- Domain Rating
- 51
oMLX Alternatives
port22
www.tryport22.com
port22 is an iOS app and macOS agent for monitoring and controlling coding-agent sessions running in a terminal. It streams transcripts to iPhone, sends input alerts, and supports Claude Code, Codex, and OpenCode.
AlphaProxy
alphaproxy.ai
AlphaProxy is an OpenAI-compatible gateway for routing requests across 450+ models and 100+ providers, with an agent runtime for multi-step work and scheduled workflows—one endpoint for model access, connected tools, and verifiable outputs.
CybeDefend
www.cybedefend.com
CybeDefend is a code security platform built for AI coding workflows. Its VibeDefend layer reviews agent prompts and diffs, enforces project and business rules, guards against risky actions, and combines code, dependency, secret, infrastructure, and CI/CD scanning before a pull request.
session-indexer
valpere.github.io
session-indexer is a GitHub-hosted developer tool that indexes Claude Code session transcripts in SQLite and lets you search them semantically. It’s designed for per-project retrieval across JSONL session history, with FTS5 as a fallback when embedding-based retrieval isn’t available.
cmux
cmux.com
Native macOS terminal for AI coding agents and CLI workflows
Weave Router
weaveos.com
Weave Router is an intelligent model router for coding agents. It evaluates coding tasks and routes requests across open and closed models, helping developers keep existing agent workflows while managing speed, quality, and model spend.