

Open-source inference server that profiles your hardware, picks and tunes the best local models for it, and plugs them into the coding agent you already use.

Open-source inference server that profiles your hardware, picks and tunes the best local models for it, and plugs them into the coding agent you already use.
Magnitude is an open-source inference server that lets an existing coding agent run entirely on local models. Rather than asking you to research quantizations and context limits, it profiles the machine it is installed on, recommends the models that actually fit that hardware, then downloads, tunes, and serves them. Setup is agent-first: you paste a single prompt into your harness and the agent walks you through profiling, model selection, download, and switching itself over to the local endpoint, or you can run the interactive CLI installer manually. Magnitude connects to Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline, and also ships its own built-in harness for people who do not already have one. Because everything runs on device, there are no token costs, API keys, or rate limits, and models, prompts, and files never leave the machine. It supports macOS and Linux natively and Windows through WSL.
Open-source inference server that profiles your hardware, picks and tunes the best local models for it, and plugs them into the coding agent you already use.
Magnitude works by combining Hardware Profiling: Inspects your CPU, GPU, and memory and recommends only the local models that will actually run well on that machine., Automatic Model Setup: Downloads, tunes, and serves the models you select so you never hand-configure quantization, context length, or serving flags., Agent-First Installation: Send one prompt to your existing coding agent and it profiles the hardware, walks you through model choice, and switches itself over to the local endpoint., Broad Harness Compatibility: Works as a drop-in backend for Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline., Built-In Harness: Ships its own agent harness for users who want local coding assistance without adopting a separate client. to help users with Private Codebase Work: Run an agent against proprietary source without sending any of it to a hosted model provider., Zero-Cost Development: Replace metered API calls with local inference for high-volume experimentation and long agent runs., Offline and Air-Gapped Environments: Keep a coding agent working on a plane, in a secure facility, or anywhere with no reliable network., Hardware Evaluation: Discover which local models a given laptop or workstation can realistically serve before committing to a setup., Existing Agent Migration: Point a harness you already use at a local backend without changing your workflow or tooling..
Key features include Hardware Profiling: Inspects your CPU, GPU, and memory and recommends only the local models that will actually run well on that machine., Automatic Model Setup: Downloads, tunes, and serves the models you select so you never hand-configure quantization, context length, or serving flags., Agent-First Installation: Send one prompt to your existing coding agent and it profiles the hardware, walks you through model choice, and switches itself over to the local endpoint., Broad Harness Compatibility: Works as a drop-in backend for Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline., Built-In Harness: Ships its own agent harness for users who want local coding assistance without adopting a separate client..
Magnitude is useful for anyone interested in Private Codebase Work: Run an agent against proprietary source without sending any of it to a hosted model provider., Zero-Cost Development: Replace metered API calls with local inference for high-volume experimentation and long agent runs., Offline and Air-Gapped Environments: Keep a coding agent working on a plane, in a secure facility, or anywhere with no reliable network., Hardware Evaluation: Discover which local models a given laptop or workstation can realistically serve before committing to a setup., Existing Agent Migration: Point a harness you already use at a local backend without changing your workflow or tooling..
Magnitude is free to use.
Visit https://github.com/magnitudedev/magnitude to sign up and explore Magnitude.
Browse by use case: Code Generation
Compare Magnitude: vs BrickForgerAI · vs AI Toolbox · vs Ponytail · vs dif.sh