Run Codex, Claude Code, and Hermes Locally with a Unified Docker Container

Описание и применение

Разработчики могут запускать Codex, Claude Code и Hermes локально в одном Docker‑контейнере, используя унифицированный протокол, что упрощает настройку и устраняет зависимость от облачных сервисов.

Задача

Developers need to run multiple LLM agents (Codex, Claude Code, Hermes) on their own machines without relying on cloud APIs.

Результат

Developers can run Codex, Claude Code, and Hermes locally in a single container, simplifying setup and eliminating cloud dependencies.

Рабочий процесс

• 1. Clone the HarnessRouter repository: git clone https://github.com/HarnessRouter/harnessrouter
• 2. Build or pull the Docker image: docker pull harnessrouter/harnessrouter:latest
• 3. Configure environment variables (e.g., model paths, API keys if needed).
• 4. Run the container: docker run -p 8000:8000 -e MODEL_PATH=/models -v /local/models:/models harnessrouter/harnessrouter:latest
• 5. Send requests to the unified endpoint (e.g., http://localhost:8000/run) using the same payload format for any agent.

Доказательства

Runs agents like Codex, Claude Code, and Hermes on your own machine using a single Docker container and unified protocol.

Источник