OpenAI-compatible API server for Apple on-device models
Rohan Paul on Twitter / X
👨🔧 Github: Native, Apple Silicon–only local LLM server. Similar to Ollama, but built on Apple's MLX- OpenAI API compatible, - Ollama‑compatible- OpenAI‑style tools + tool_choice, with tool_calls parsing and streaming deltasgithub. com/dinoki-ai/osaurus pic.twitter.com/G0NbWnEJcQ— Rohan Paul (@rohanpaul_ai) September 3, 2025
Apple not paying OpenAI to use ChatGPT in iOS 18: report
At WWDC on Monday, Apple announced its highly-anticipated partnership with OpenAI to bring ChatGPT to iOS 18. While Apple and...
OpenAI to acquire Ona
OpenAI plans to acquire Ona to expand Codex with secure, persistent cloud environments, enabling long-running AI agents across enterprise workflows.
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.
Arthur-Ficial/apfel
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
OpenAI Model Spec
The Model Spec specifies desired behavior for the models underlying OpenAI's products (including our APIs).
OpenAI on Twitter / X
Our open models are here.Both of them.https://t.co/9tFxefOXcg— OpenAI (@OpenAI) August 5, 2025
Use OpenAI's Responses API with local models
OpenAI-compatible `/v1/responses` endpoint (stateful chats, remote mcp, custom tools)
Secure MCP Tunnel | OpenAI API
Connect private or on-prem MCP servers to supported OpenAI products with an outbound-only MCP tunnel, without exposing them to the public internet.
Latency optimization | OpenAI API
Improve latency across a wide variety of LLM-related use cases.
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]
Nailed it, @komorama.bsky.social We have a huge opportunity here – there's no reason the future user interface for *all your computing* needs to be tied to OpenAI. We can build a new, uniquely personal computer that you own, without your entire digital life being locked to one company or provider.
