ai-mocks
Introduction: AI-Mocks is a Kotlin-based mock server toolkit that brings service virtualization to both HTTP/SSE and LLM APIs — think WireMock meets local OpenAI/Anthropic/Gemini/A2A testing, but with real streaming and Server-Sent Events support.
Tags:
AI-Mocks are mock LLM (Large Language Model) servers built on Mokksy, a mock server inspired by WireMock, with support for response streaming and Server-Side Events (SSE). They are designed to build, test, and mock LLM responses for development purposes.
Mokksy
Mokksy is a mock HTTP server built with Kotlin and Ktor. It addresses the limitations of WireMock by supporting true SSE and streaming responses, making it extreamly useful for integration testing LLM clients.
AI-Mocks
AI-Mocks is a set of specialized mock server implementations (e.g., mocking OpenAI API) built using Mokksy.
It supports mocking following AI services:
- OpenAI - ai-mocks-openai
- Anthropic - ai-mocks-anthropic
- Google VertexAI Gemini - ai-mocks-gemini
- Ollama - ai-mocks-ollama
- Agent-to-Agent (A2A) Protocol - ai-mocks-a2a
Feature Support Matrix
| Feature | OpenAI | Anthropic | Gemini | Ollama | A2A |
|---|---|---|---|---|---|
| Chat Completions | ✅ | ✅ | ✅ | ✅ | ✅ |
| Streaming | ✅ | ✅ | ✅ | ✅ | ✅ |
| Embeddings | ✅ | ❌ | ❌ | ✅ | ❌ |
| Moderation | ✅ | ❌ | ❌ | ❌ | ❌ |
| Additional APIs | Responses | - | - | Generate | Full A2A Protocol (11 endpoints) |
How to build
Building project locally:
./gradlew build
or using Make:
make
Contributing
I do welcome contributions! Please see the Contributing Guidelines for details.
