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 est un serveur d’inférence LLM natif pour macOS, basé sur MLX, qui exécute localement sur Apple Silicon des modèles compatibles de langage, vision-langage, embeddings et reranking. Conçu pour les workflows d’agents de programmation, il fonctionne avec Claude Code, OpenClaw, Cursor et les clients compatibles avec OpenAI.
Qu'est-ce que 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.
Que peut faire oMLX ?
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.
Cas d'utilisation
“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.
Questions fréquentes
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.
Informations rapides
- 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
Analyse du trafic de oMLX
Les données de trafic sont fournies à titre indicatif uniquement.
- Évaluation du domaine
- 51
Alternatives à oMLX
cmux
cmux.com
Terminal macOS natif pour agents de code IA et workflows CLI
CybeDefend
www.cybedefend.com
CybeDefend est une plateforme de sécurité du code conçue pour les workflows de programmation avec l’IA. Sa couche VibeDefend examine les prompts des agents et les diffs, applique les règles du projet et de l’entreprise, protège contre les actions risquées et regroupe les analyses du code, des dépendances, des secrets, de l’infrastructure et du CI/CD avant une pull request.
session-indexer
valpere.github.io
session-indexer est un outil pour développeurs hébergé sur GitHub qui indexe les transcriptions de sessions Claude Code dans SQLite et permet de les rechercher par sens. Il est conçu pour retrouver l’historique JSONL par projet, avec FTS5 en solution de repli lorsque la recherche basée sur des embeddings n’est pas disponible.
SkillsMP
skillsmp.com
SkillsMP est une marketplace gratuite pour découvrir des compétences d’agents open source dans des dépôts GitHub publics, avec recherche, navigation, API REST et accès MCP pour Claude Code, Codex CLI et ChatGPT.
Million Software, Inc.
million.dev
Vérification pour agents de programmation IA afin de prouver que le code fonctionne
Prompt Genie
prompt-genie.com
Gestion et optimisation des prompts avec mémoire Claude Code pour les workflows IA