Rohan Paul on Twitter / X

tijs/mei

Native Swift/MLX OpenAI-compatible inference server for Apple Silicon

gety-ai/apple-on-device-openai

OpenAI-compatible API server for Apple on-device models

BerriAI/litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Osaurus — Own Your AI on Apple Silicon

Own your AI: local-first agents with memory, tools, and identity on Apple Silicon. Offline, open source, and API-compatible with OpenAI, Anthropic, and Ollama.

Osaurus — Own Your AI on Apple Silicon

Own your AI: local-first agents with memory, tools, and identity on Apple Silicon. Offline, open source, and API-compatible with OpenAI, Anthropic, and Ollama.

OpenAI Developers on Twitter / X

Today we’re announcing Open Responses: an open-source spec for building multi-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API.✅ Multi-provider by default✅ Useful for real-world workflows✅ Extensible without fragmentationBuild… pic.twitter.com/SJiBFx1BOF— OpenAI Developers (@OpenAIDevs) January 15, 2026

Ollama is now powered by MLX on Apple Silicon in preview· Ollama Blog

Today, we're previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple's machine learning framework.

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.

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

MLX on Mac with Apple silicon lets AI researchers and developers experiment locally with the latest models and methods in a private…

Latency optimization | OpenAI API

Improve latency across a wide variety of LLM-related use cases.

Issue · BerriAI/litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr...

OpenAI on Twitter / X

Our open models are here.Both of them.https://t.co/9tFxefOXcg— OpenAI (@OpenAI) August 5, 2025

OpenAI gpt-oss· Ollama Blog

Ollama partners with OpenAI to bring gpt-oss to Ollama and its community.

Stream29/ProxyAsLocalModel

Proxy remote LLM API as Ollama and LM Studio, for using them in JetBrains AI Assistant