Teams building on aimock
Start with LLM mocking. Add MCP, A2A, vector, and more when you need them. The aimock suite grows with your stack.
npx -p @copilotkit/aimock llmock -f ./fixtures
docker run -v $(pwd)/fixtures:/fixtures -p 4010:4010 ghcr.io/copilotkit/aimock -h 0.0.0.0 -f /fixtures
Or install as a library: npm install @copilotkit/aimock
{ "match": { "userMessage": "Hello" }, "response": { "content": "Hi there! How can I help?" }, "opts": { "chunkSize": 10, "latency": 1000 } }
Teams building on aimock
Proxy unmatched requests to real APIs and capture every response.
Fixtures written to disk automatically as clean, editable JSON.
Deterministic responses in CI, forever. No API keys, no flakiness.
$ npx -p @copilotkit/aimock llmock --record --provider-openai https://api.openai.com ⚡ Listening on http://localhost:4010 ⚠ NO FIXTURE MATCH — proxying to https://api.openai.com/v1/chat/completions ✓ Recorded → fixtures/recorded/openai-2026-03-31T22:15:00.json ⚡ Fixture match — replaying from disk
One JSON config. One port. Every service your AI app depends on.
{ "llm": { "fixtures": "./fixtures/llm", "providers": ["openai", "claude", "gemini"] }, "mcp": { "tools": "./fixtures/mcp/tools.json", "resources": "./fixtures/mcp/resources.json" }, "a2a": { "agents": "./fixtures/a2a/agents.json" }, "vector": { "provider": "pinecone", "fixtures": "./fixtures/vector" } }
$ npx @copilotkit/aimock --config aimock.json ⚡ aimock v1.44.0 ✓ LLM mounted at /v1/chat/completions ✓ LLM mounted at /v1/messages ✓ LLM mounted at /v1/embeddings ✓ MCP mounted at /mcp/tools/* ✓ A2A mounted at /a2a/agents/* ✓ Vector mounted at /vectors/* ⚡ Listening on http://localhost:4010 6 services · 24 fixtures loaded
OpenAI, Claude, Gemini, Gemini Interactions, Bedrock, Azure, Vertex AI, Ollama, Cohere, OpenRouter, ElevenLabs — full streaming and embeddings support for every provider.
Mock tools, resources, and prompts with full session management. Script each test's tool answers in its fixture file: ordered results, exact-argument checks, and a closed-world mode that fails on any undeclared tool.
Agent cards, message routing, and SSE streaming. Mock multi-agent interactions with deterministic responses.
Mock agent-to-UI event streams for CopilotKit frontend testing.
Pinecone, Qdrant, and ChromaDB compatible. Mock similarity search, upserts, and index operations with fixtures.
Transport faults (drop, malformed, disconnect, 429) and model misbehavior: broken tool-call JSON, schema violations, unknown tools, and max-tokens cutoffs in every provider's real wire format.
Image generation and editing, text-to-speech (OpenAI + ElevenLabs), audio transcription and translation, non-speech audio generation, and video generation — mock every multimedia endpoint with fixtures.
Zero-config useAimock() with auto server lifecycle, env var patching, and
match count reset.
Fixtures stay accurate as providers evolve. Fixes ship before your tests break.
LLM providers change their response formats without warning. aimock catches it within 24 hours and ships the fix before your tests break.
Daily CI hits actual OpenAI, Anthropic, Gemini endpoints to detect response format changes.
Response schemas are validated against aimock's builders. Any drift is flagged automatically.
Drift detected → fixtures, builders, skills, and docs updated → PR shipped. Always current, within a day.
| Capability | aimock | MSW | VidaiMock | mock-llm | piyook/llm-mock | mokksy/ai-mocks | MockServer | WireMock |
|---|---|---|---|---|---|---|---|---|
| Cross-process interception | Real server ✓ | In-process only | ✓ | ✓ (Docker) | ✓ | ✓ (Ktor) | ✓ | ✓ |
| Chat Completions SSE | Built-in ✓ | manual | ✓ | ✓ | ✓ | ✓ | ✓ | Not documented |
| Responses API SSE | Built-in ✓ | manual | ✓ | ✗ | ✗ | ✓ | ✓ | Not documented |
| Claude Messages API | Built-in ✓ | manual | ✓ | ✗ | ✓ | ✓ | ✓ | Not documented |
| Gemini streaming | Built-in ✓ | manual | ✓ | ✗ | ✓ | ✓ | ✓ | Not documented |
| Multi-provider support | 13 providers (15 API surfaces) ✓ | manual | 12 providers | OpenAI only | OpenAI only | 5 providers | ✓ | Not documented |
| OpenRouter router / fallback simulation | Deterministic ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | partial | Not documented |
| WebSocket APIs | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | partial | partial |
| Embeddings API | Built-in ✓ | ✗ | ✓ | ✗ | ✓ | ✓ | ✓ | Not documented |
| Image generation | Built-in ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | Not documented |
| Image editing | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented |
| Text-to-Speech | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented |
| Audio transcription | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| Audio translation | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| Non-speech audio | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented |
| Video generation | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| AG-UI event mocking | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| MCP tool mocking | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | Not documented |
| Scenario-scoped MCP tool fakes | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| Fail on undeclared MCP tool | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| A2A agent mocking | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✓ | ✓ | Not documented |
| Vector DB mocking | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | Not documented | Not documented |
| Search & rerank | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | partial | Not documented |
| Record & replay | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | ✓ (HTTP) |
| Drift detection | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | partial | ✗ |
| Sequential / stateful responses | Built-in ✓ | manual | ✓ | ✓ | ✗ | ✗ | ✓ | ✓ (HTTP) |
| Request journal | ✓ | manual | ✓ | ✗ | ✓ | ✗ | ✓ | ✓ |
| Error injection | ✓ | ✓ | partial | ✗ | ✗ | ✗ | ✓ | ✓ (HTTP) |
| Chaos testing | Built-in ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | HTTP faults and delays |
| Model misbehavior faults (tool-call JSON, schema, unknown tool, stop reasons) | Built-in ✓ | Not documented | Not documented | Not documented |
Partial stop-reason controls |
Partial stop-reason controls OpenAI / Anthropic |
Partial | Not documented |
| Streaming physics | Built-in ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | partial |
| Structured output / JSON mode | Built-in ✓ | manual | ✓ | ✗ | ✗ | ✗ | ✓ | Not documented |
| Programmatic API | ✓ (TypeScript/JS) | ✓ (TypeScript/JS) | No (binary only) | ✗ | ✗ | ✓ (Kotlin/JVM) | ✓ (8 languages) | ✓ (Java/JVM) |
| Fixture files | JSON ✓ | Code-only | Tera templates | YAML config | JSON templates | ✗ | ✓ (JSON) | ✓ (JSON) |
| GitHub Action | Built-in ✓ | ✗ | ✗ | ✗ | ✓ | ✓ | ✓ | Not documented |
| Vitest / Jest plugins | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | partial | Not documented |
| Docker + Helm | Both ✓ | ✗ | Docker only | ✓ (Both) | Docker only | ✗ | ✓ | ✓ (Helm experimental) |
| Prometheus metrics | Built-in ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | partial |
| Streaming usage chunks | Built-in ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | partial | Not documented |
| Rate limiting headers | Built-in ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | partial | Not documented |
| Dependencies | Zero ✓ | ~300KB | Zero (Rust) | Node+Express | Minimal | JVM (Kotlin) | JVM, or JVM-less binary | JVM |
Requires 1.45.0+
| Capability | aimock MCP fakes | Mastra Experiment Tool Mocks | MockServer MCP mocking |
|---|---|---|---|
| Works with any agent framework | ✓ (over MCP HTTP) | ✗ | ✓ (over MCP HTTP) |
| MCP tools | ✓ | Not documented | ✓ |
| In-process (non-network) tools | ✗ (runs out of process by design) | ✓ | n/a |
| Ordered answers per tool | ✓ | ✓ | Not documented |
| Exact-argument matching | ✓ | ✓ | Not documented |
| Any-argument matching | ✓ | ✓ | ✓ (one answer for every call) |
| Fail on undeclared tool | ✓ | ✓ | Not documented |
| Scripted tool errors | ✓ | Not documented | ✓ |
| Per-test state and reset | ✓ | ✓ | Not documented |
| LLM responses mocked in the same scenario | ✓ | Not documented | partial |
| Create fakes from recorded runs | ✓ (record live MCP, replay offline) | partial | ✓ |
| Report unused mocks | ✓ (per test; can fail the test) | ✓ | Not documented |
| Workflow / multi-step pipeline targets | ✓ (any caller over MCP HTTP) | Planned | ✓ (any caller over MCP HTTP) |
AG-UI uses aimock for its end-to-end test suite, verifying AI agent behavior across LLM providers with fixture-driven responses in the codebase. Browse the example fixtures to get started.
MSW