Localharness

Open-source, model-agnostic agent harness for local LLMs, defined in YAML.

PlatformWebfreeglobal

Localharness is an open-source, model-agnostic agent harness for local LLMs, letting developers define agents in YAML with tools, memory and deny-first permissions and run them against any OpenAI-compatible endpoint like vLLM, Ollama or llama.cpp. It's aimed at developers building agents on local inference backends who want a declarative, provider-independent harness.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Localharness - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Localharness to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Localharness (or something else) actually fits.

Try a problem