llm-ferry
PulseGate's liveness check found it on 18 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 18 Sep 2026. How this is checked
llm-ferry is a self-hosted AI gateway for macOS that exposes local MLX models through an OpenAI-compatible LAN endpoint. It can fall back to cloud API keys, giving developers a unified interface for local and hosted language-model inference.
Inferred · not functionally tested
Overview
6 featuresPurpose: Serving local and cloud language models through one OpenAI-compatible endpoint on Apple Silicon Macs.
Inferred · not functionally tested
Audience: developers running LLMs on Apple Silicon Macs
Inferred · not functionally tested
Functions: Unknown
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted, macos, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
llm-ferry is an Inference & model serving project. Inferred · not functionally tested: It focuses on serving local and cloud language models through one OpenAI-compatible endpoint on Apple Silicon Macs. Inferred · not functionally tested: llm-ferry is an open-source project aimed at developers running LLMs on Apple Silicon Macs. Basis unknown · not verified: llm-ferry is open source under the MIT license. Basis unknown · not verified: llm-ferry is available on the command line, macOS, and API, and it can be self-hosted.
Behind llm-ferry is sblattj, and it first shipped in 2026. The project is developed in the open on GitHub with 226 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are LAN endpoint, MLX model serving, and Cloud API fallback. Inferred · not functionally tested: Catalogued interfaces include a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- LAN endpoint
- MLX model serving
- Cloud API fallback
- OpenAI compatibility
- Self-hosted deployment
- Local inference
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit 390c20aae05c · since Sep 2026
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about llm-ferry
- What is llm-ferry?
- Inferred · not functionally tested: Llm-ferry focuses on serving local and cloud language models through one OpenAI-compatible endpoint on Apple Silicon Macs. It is catalogued under Inference & model serving on PulseGate.
- Who should use llm-ferry?
- Inferred · not functionally tested: llm-ferry is an open-source project built for developers running LLMs on Apple Silicon Macs.
- Does llm-ferry have a free plan?
- Basis unknown · not verified: Yes — llm-ferry is open source under the MIT license and free to use.
- What platforms does llm-ferry run on?
- Basis unknown · not verified: llm-ferry runs on the command line, macOS, and API. It can also be self-hosted.
- Is llm-ferry still active?
- PulseGate's liveness check found it on 18 Sep 2026. Its GitHub repository shows 226 commits in the last 90 days.
- What are alternatives to llm-ferry?
- Similar projects tracked by PulseGate include fastllm-proxy, Enterprise AI Gateway, and FreeModel.fastllm-proxyEnterprise AI GatewayFreeModel
- Who makes llm-ferry?
- llm-ferry is developed by sblattj.
- How long has llm-ferry been around?
- llm-ferry first shipped in 2026.
Similar projects
Closest matches by what these projects do