airlock-llm is an open-source proxy for large language models, offering logging, guardrails, and unified access for AI-powered coding tools. It helps enterprises secure and monitor LLM usage, enforce compliance, and manage sensitive data. Built on LiteLLM, it is suitable for platform engineers and AI infrastructure teams.
airlock-llm is a LLM eval & observability project. Securing, monitoring, and managing access to large language models in enterprise environments. It is built as an open-source project for enterprise AI platform engineers and developers. The project is open source (Apache-2.0). It runs on the web and the command line, and it can be self-hosted.
Corey T. and contributors builds and maintains airlock-llm, and it first shipped in 2026. The project is developed in the open on GitHub with 296 commits in the last 90 days. Among its 6 catalogued features are LLM proxy, logging, and guardrails. It exposes integrations via a public API.
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