Run Claude Code with any foundation model on Amazon Bedrock (43 models) or a self-hosted model on EC2. Includes a HumanEval benchmark.
Claude Code Multi-Model is a sample project that connects Anthropic’s command-line coding agent to foundation models hosted on Amazon Bedrock or self-hosted on EC2, then evaluates their coding performance. It is intended for demonstration and learning, helping users compare models for software-engineering tasks and function-generation benchmarks. The catalogue add-ons support model selection and evaluation workflows.
These files are aws-samples/sample-claude-code-multi-model's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 479 tok CLAUDE.md A 48 tok .claude/skills/implement/SKILL.md A 95 tok .claude/skills/summarize/SKILL.md A 81 tok .claude/skills/swe/SKILL.md A 100 tok .claude/skills/vllm-setup/SKILL.md C 164 tok