localm is an open-source local AI platform for offline LLM inference and model management. It supports GGUF and Llama-oriented workflows and provides extensible agent plugins, including MCP-related capabilities, for developers running AI locally.
localm sits in PulseGate's Inference & model serving category. It focuses on running and managing language models locally without relying on hosted AI services. localm is an open-source project aimed at developers building offline AI applications and agents. localm is open source under the AGPL-3.0 license. It ships for the command line, and it can be self-hosted.
Matlan1 builds and maintains localm, and it first shipped in 2026. Development happens publicly on GitHub with 1.8k commits in the last 90 days. Key capabilities include offline inference, model management, and GGUF support. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do