Show HN: Lite-Harness – Self-Hosted Cursor Agents (Use Claude Code/OpenCode) (github.com)

Lite-Harness, a new self-hosted framework by LiteLLM Labs, allows users to run AI models like Claude Code, Codex, and OpenCode in a streamlined manner using a single server environment. By leveraging Docker, users can easily deploy the framework and interact with various AI agents through a command-line interface (CLI) or an OpenCode-compatible API. The system supports persistent session management, allowing for continuity across server restarts, which addresses common complexities faced when running multiple AI services separately. This initiative is significant for the AI/ML community as it simplifies the integration and management of different AI models under one unified platform, ultimately reducing maintenance efforts. With support for automation tasks—such as monitoring CI and fetching GitHub stargazers—Lite-Harness enhances operational efficiency for developers. The project’s open-source nature, released under the MIT license, encourages collaboration and further innovation in the AI ecosystem, making it a valuable tool for teams looking to integrate AI capabilities seamlessly into their workflows.