ai-mocks
🤖 AI-Mocks is a Kotlin-based toolkit for mocking and testing LLM APIs with real streaming and SSE support. Simulate OpenAI, Anthropic, Gemini, Ollama, and A2A services locally for reliable integration testing.
In the AI payments ecosystem
ai-mocks is a growing Kotlin project in the AI payments / x402 ecosystem, focused on a2a-protocol, agent-to-agent, kotlin, ktor. It currently has 52 GitHub stars and 4 forks, and sits alongside related tools like LeapRAG, fastapi-a2a, Sae, aser, a2a-go, local-operator.
AI-Mocks
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.
Similar projects
LeapRAG is an open-source platform that integrates advanced RAG technology with Google’s A2A protocol, enabling users to build context-aware, data-driven agents. These agents are automatically A2A-compliant and can be discovered and used by any compatible client without extra development.
A zero-friction FastAPI plugin that turns any existing app into a fully compliant Agent-to-Agent (A2A) node — expose your routes as discoverable skills and delegate tasks to remote agents with a single decorator.
A lawyer for the agent economy. AI agents can request contract review, risk analysis, and legal guidance via A2A protocol.
Aser is a lightweight, self-assembling AI Agent frame.
Golang SDK for A2A Protocol
AI agents platform that gives you a workspace with an integrated team of personal assistants that can work behind the scenes to handle daily monotonous tasks.
More LLM projects
All LLM projects →
The agent-native LLM router for autonomous agents. 55+ models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.
The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.
Daydreams is a set of tools for building agents for commerce
Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.