A directory of services AI agents can actually use — APIs, tools and merchants with machine-readable interfaces and agent payment protocols. Badges are probe-backed, never self-asserted.
| Score |
|---|
 Google Gemini APIOpenAPIMPP Gemini multimodal models via Google AI Studio and Vertex AI, with function calling and MCP support | Models | ||
 Hugging Face InferenceMCPOpenAPI Serverless and dedicated inference for open models, plus a hosted MCP endpoint over Hub tools | Models | ||
 LangfuseMCPOpenAPIllms.txt Open-source LLM and agent observability — traces, evals, prompt management, and cost tracking | Observability | ||
 LangGraph PlatformMCPOpenAPI Hosted runtime for stateful agent graphs with persistence, streaming, and human-in-the-loop | Platforms | ||
 LangSmithMCPOpenAPI Tracing, evals, and prompt management with the deepest LangChain and LangGraph integration | Observability | ||
 LettaMCPOpenAPIllms.txt Stateful agent runtime where memory is the agent — self-editing core memory, archival recall, and a REST API | Memory | ||
 LiteLLMMCPOpenAPI Open-source proxy and SDK exposing 100+ model providers behind one OpenAI-compatible API | Models | ||
 LiveKitMCPOpenAPIllms.txt Open-source realtime media infrastructure with the Agents framework, SIP, and phone numbers | Messaging | ||
 Machine Payments Protocol (MPP)MCPOpenAPIllms.txtMPP Open HTTP payment standard from Stripe and Tempo covering one-shot, recurring, and streaming agent payments across cards, stablecoins, and Lightning | Payments | ||
 Mem0MCPOpenAPIllms.txt Managed memory layer that extracts, dedupes, and retrieves long-term memories per user, agent, or session | Memory | ||
 ModalMCPOpenAPIllms.txtMPP Serverless GPU and CPU compute defined in Python, with sandboxes and pay-per-second MPP billing | Compute | ||
 n8nMCPOpenAPIllms.txt Open-source workflow automation with a public API, webhook triggers, and MCP nodes | Platforms | ||
 NeonMCPOpenAPIllms.txt Serverless Postgres with instant branching, autoscaling, and a remote MCP server | Memory | ||
 OpenAI APIOpenAPIACPMPP GPT-5 series models, embeddings, and the Responses API with native MCP and tool use | Models | ||
 OpenRouterOpenAPIllms.txt One OpenAI-compatible endpoint in front of hundreds of hosted models, with automatic fallback and per-key spend limits | Models | ||
 ParallelMCPOpenAPIllms.txt Search and deep-research APIs built for agents, with tiered latency and citation-grade results | Search | ||
 PineconeMCPOpenAPIllms.txt Managed vector database with serverless indexes, integrated embedding, and an assistant MCP server | Memory | ||
 Pipedream ConnectMCPOpenAPI Managed auth and 2,500+ app APIs agents can call directly, plus MCP servers per app | Platforms | ||
 QdrantMCPOpenAPIllms.txt Open-source vector search engine with managed cloud and an official MCP server | Memory | ||
 ReplicateOpenAPIllms.txt Run thousands of open-source models — LLM, image, video, audio — behind one API | Models |
Same query as JSON: /api/v1/services?auth_method=api-key&page=2