Serve the MLX models your cocore agent runs locally to your own tools without round-tripping through the cocore network.
MLX India Community Meetup 2 | Own Your AI by Ankesh Bharti
GradientHQ/parallax
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
Improving LM Studio's MLX Engine for Agentic Workflows
mlx-engine v1.8.5 dramatically improves performance for repeated, long-context agentic workflows by checkpointing your KV cache.
Why MLX — Prince Canuma, Neywa Labs
freestylefly/wesight
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
Unsloth AI on Twitter / X
Run Gemma 3n locally with our Dynamic GGUFs!✨@Google's Gemma 3n supports audio, vision, video & text and the 4B model fits on 8GB RAM for fast local inference.Fine-tuning is also supported in Unsloth.Gemma-3n-E4B GGUF: https://t.co/PliynxoKQc https://t.co/wMFWLjNaDR pic.twitter.com/lxsMNDmkW8— Unsloth AI (@UnslothAI) June 26, 2025
Msty Nexus - Inference Gateway
Put one governed inference layer behind your AI tools for model routing, local runtimes, provider keys, usage visibility, and guardrails.
mlx-examples/stable_diffusion at main · ml-explore/mlx-examples
Examples in the MLX framework. Contribute to ml-explore/mlx-examples development by creating an account on GitHub.
Mlem - A Beautiful iOS Client for Lemmy
Mlem is a beautiful, intuitive open source iOS client for Lemmy that lets you effortlessly participate in conversations across all Lemmy servers.
raullenchai/Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
raullenchai/Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Release v0.29.0 · ml-explore/mlx
Highlights Support for mxfp4 quantization (Metal, CPU) More performance improvements, bug fixes, features in CUDA backend mx.distributed supports NCCL back-end for CUDA What's Changed [CUDA]...
Tiles
A local-first, collaborative AI assistant that works for you. Built with open models and decentralized protocols.
Did an afternoon / evening speedrun of setting up local AI on the @z-space.ca network with @jacob.cascadia.social @vangarderen.net @hadsie.com - proxmox node for openwebui, npm - ASUS GX10 node for inference - Old Macbook running LiteLLM for routing between machines
