claude-code-proxy vs kong
API proxy projects compared
claude-code-proxy translates Anthropic-format requests so clients such as Claude Code can use OpenAI, Gemini, or Anthropic backends. kong is a broader gateway for routing and governing API, AI, and MCP traffic, with shared controls for services.

claude-code-proxy: Connect Claude Code to Other Model Providers
A Python proxy that lets Anthropic-compatible clients such as Claude Code use OpenAI, Gemini, or Anthropic backends through LiteLLM. It suits developers who want to route Claude-style requests to another provider.

kong: Route and Govern API, LLM, and MCP Traffic
Kong Gateway is a cloud-native, platform-agnostic API, LLM, and MCP gateway built in Lua. It centralizes traffic routing, security, and extensibility for teams running services on their own infrastructure or Kubernetes.
| claude-code-proxy | kong | |
|---|---|---|
| Language | Python | Lua |
| License | — | Apache-2.0 |
| Stars | 3.8k | 44.3k |
| Forks | 494 | 5.2k |
| Last analyzed | Oct 9, 2026 | Oct 20, 2026 |
Key differences
- claude-code-proxy focuses on translating Anthropic API requests between clients and model providers, while kong handles API traffic and shared gateway controls across services.
- claude-code-proxy is written in Python and uses LiteLLM for translation; kong is written in Lua and extends gateway behavior through plugins.
- claude-code-proxy supports configurable Claude-style model mappings and streaming or non-streaming responses; kong includes routing, load balancing, authentication, and rate limiting.
- claude-code-proxy can run from source with uv or as a Docker container; kong documents Docker Compose with PostgreSQL and a separate DB-less Docker setup.
- claude-code-proxy has 3.8k stars and 492 forks; kong has 44.2k stars and 5.2k forks.
- kong specifies an Apache-2.0 license; claude-code-proxy is described as having no license specified in the provided repository metadata.
Choose claude-code-proxy if you…
- want to keep an Anthropic-compatible client workflow while using OpenAI or Gemini models.
- need configurable mappings between Claude-style model requests and provider models.
- want a focused proxy that can route to Anthropic directly as well as other supported providers.
Choose kong if you…
- need shared gateway controls such as authentication, rate limiting, and request transformations across services.
- want to route API, LLM, or MCP traffic through a common gateway layer.
- operate services across Kubernetes or other infrastructure and need plugin-based gateway behavior.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.