{"id":23751,"date":"2010-02-26T00:51:24","date_gmt":"2010-02-26T00:51:24","guid":{"rendered":"https:\/\/scannn.com\/magnitudedev-magnitude-open-source-inference-server-that-runs-the-best-local-models-for-your-hardware-plugged-into-the-agent-you-already-use-works-with-pi-opencode-hermes-openclaw-codex-claude\/"},"modified":"2010-02-26T00:51:24","modified_gmt":"2010-02-26T00:51:24","slug":"magnitudedev-magnitude-open-source-inference-server-that-runs-the-best-local-models-for-your-hardware-plugged-into-the-agent-you-already-use-works-with-pi-opencode-hermes-openclaw-codex-claude","status":"publish","type":"post","link":"https:\/\/scannn.com\/lv\/magnitudedev-magnitude-open-source-inference-server-that-runs-the-best-local-models-for-your-hardware-plugged-into-the-agent-you-already-use-works-with-pi-opencode-hermes-openclaw-codex-claude\/","title":{"rendered":"magnitudedev\/magnitude: Open source inference server that runs the best local models for your hardware, plugged into the agent you already use. Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline. \u00b7 GitHub"},"content":{"rendered":"\n
\n

\n
\n <\/source><\/source><\/picture><\/themed-picture><\/p>\n

Run your agent on local models. Free, private, and offline.<\/strong><\/p>\n

\n \"Documentation\"<\/a>
\n \"Discord\"<\/a>
\n \"Follow<\/a>
\n \"GitHub<\/a>
\n \"npm<\/a>\n<\/p>\n

Magnitude is an open source inference server that runs the best local models for your hardware, plugged into the agent you already use. It profiles your machine, recommends the models that fit, then downloads, tunes, and runs them. Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline, or use the built-in harness.<\/p>\n

Help us reach more developers and grow the Magnitude community. Star this repo!<\/p>\n\"Pi,
\n<\/source><\/source><\/picture><\/themed-picture>\n

Send this to your agent to walk through models and setup:<\/strong><\/p>\n

\n
Set up local models for me with the Magnitude CLI. Install it with `npm i -g @magnitudedev\/cli` (or my package manager), then run `magnitude docs onboarding` and follow the instructions.\n<\/code><\/pre>\n<\/div>\n
Your agent will profile your hardware, walk you through the best local models for it, download the ones you pick, and switch itself over to them.<\/p>\n
Magnitude supports macOS and Linux. Windows is supported through WSL.<\/p>\n
\nWant to browse the models directly?<\/summary>\n
\n
npm i -g @magnitudedev\/cli\nmagnitude setup<\/pre>\n<\/div>\n
The interactive setup lets you browse the recommended models and choose one yourself.<\/p>\n<\/details>\n