OpenLIT is an open-source agent harness engineering platform: OpenTelemetry-native agent observability, evals, guardrails, prompt management, and cost and GPU monitoring for AI agents and coding agents. Free to self-host under Apache 2.0. We help teams trace, evaluate, guard, and improve everything around the model in production.
We are excited about the potential of LLMs and generative AI, and the impact they will have on how software gets built. Doing our part to accelerate that shift is our mission.
OpenLIT started from the pain of shipping LLM apps without clear traces, cost, quality, or agent visibility. The answer was an OpenTelemetry-native AI engineering platform you can self-host free under Apache 2.0: LLM tracing, evaluations, Prompt Hub, Vault, OpenGround, coding agent monitoring, and GPU metrics in one place.
Today OpenLIT is used by developers worldwide. The project is open, community-driven, and built in public on GitHub.