Services — the AI agent directory

Google Gemini API
Gemini multimodal models via Google AI Studio and Vertex AI, with function calling and MCP support
- llm
- multimodal
- google
- +2 more
- +1 more
OpenAPIMPP
5/5
Hugging Face Inference
Serverless and dedicated inference for open models, plus a hosted MCP endpoint over Hub tools
- llm
- open-source
- models
- +2 more
- +1 more
MCPOpenAPI
5/5
Langfuse
Open-source LLM and agent observability — traces, evals, prompt management, and cost tracking
- observability
- tracing
- evals
- +3 more
- +2 more
MCPOpenAPIllms.txt
5/5
LangGraph Platform
Hosted runtime for stateful agent graphs with persistence, streaming, and human-in-the-loop
- agents
- orchestration
- stateful
- +2 more
- +1 more
MCPOpenAPI
5/5
LangSmith
Tracing, evals, and prompt management with the deepest LangChain and LangGraph integration
- observability
- tracing
- evals
- +2 more
- +1 more
MCPOpenAPI
5/5
Letta
Stateful agent runtime where memory is the agent — self-editing core memory, archival recall, and a REST API
- agent-memory
- stateful-agents
- memgpt
- +2 more
- +1 more
MCPOpenAPIllms.txt
5/5
LiteLLM
Open-source proxy and SDK exposing 100+ model providers behind one OpenAI-compatible API
- llm
- gateway
- open-source
- +2 more
- +1 more
MCPOpenAPI
5/5
LiveKit
Open-source realtime media infrastructure with the Agents framework, SIP, and phone numbers
- realtime
- voice-agents
- webrtc
- +3 more
- +2 more
MCPOpenAPIllms.txt
5/5
Machine Payments Protocol (MPP)
Open HTTP payment standard from Stripe and Tempo covering one-shot, recurring, and streaming agent payments across cards, stablecoins, and Lightning
- mpp
- payments
- protocol
- +4 more
- +3 more
MCPOpenAPIllms.txtMPP
5/5
Mem0
Managed memory layer that extracts, dedupes, and retrieves long-term memories per user, agent, or session
- agent-memory
- long-term-memory
- personalization
- +2 more
- +1 more
MCPOpenAPIllms.txt
5/5
Modal
Serverless GPU and CPU compute defined in Python, with sandboxes and pay-per-second MPP billing
- gpu
- serverless
- sandbox
- +3 more
- +2 more
MCPOpenAPIllms.txtMPP
5/5
n8n
Open-source workflow automation with a public API, webhook triggers, and MCP nodes
- automation
- workflows
- open-source
- +3 more
- +2 more
MCPOpenAPIllms.txt
5/5
Neon
Serverless Postgres with instant branching, autoscaling, and a remote MCP server
- database
- postgres
- branching
- +3 more
- +2 more
MCPOpenAPIllms.txt
5/5
OpenAI API
GPT-5 series models, embeddings, and the Responses API with native MCP and tool use
- llm
- text
- embeddings
- +4 more
- +3 more
OpenAPIACP
5/5
OpenRouter
One OpenAI-compatible endpoint in front of hundreds of hosted models, with automatic fallback and per-key spend limits
- llm
- gateway
- routing
- +2 more
- +1 more
OpenAPIllms.txt
5/5
Parallel
Search and deep-research APIs built for agents, with tiered latency and citation-grade results
- search
- research
- agents
- +2 more
- +1 more
MCPOpenAPIllms.txt
5/5
Pinecone
Managed vector database with serverless indexes, integrated embedding, and an assistant MCP server
- vector-db
- embeddings
- rag
- +2 more
- +1 more
MCPOpenAPIllms.txt
5/5
Pipedream Connect
Managed auth and 2,500+ app APIs agents can call directly, plus MCP servers per app
- automation
- integrations
- managed-auth
- +2 more
- +1 more
MCPOpenAPI
5/5
Qdrant
Open-source vector search engine with managed cloud and an official MCP server
- vector-db
- embeddings
- open-source
- +2 more
- +1 more
MCPOpenAPIllms.txt
5/5
Replicate
Run thousands of open-source models — LLM, image, video, audio — behind one API
- llm
- image
- video
- +3 more
- +2 more
OpenAPIllms.txt
5/5