-
OrchestrationLangGraph
Graph-based orchestration for stateful, multi-actor agent workflows with explicit control flow and checkpointing.
-
LLM / inferenceOpenRouter
A single OpenAI-compatible API that routes to 300+ LLMs from every major provider, with per-key budgets and programmatic key provisioning.
-
MemoryMem0
A memory layer for AI agents — extracts, stores, and retrieves user/agent facts across sessions.
-
Search & retrievalExa
Neural/semantic web search API purpose-built for AI agents, returning clean results plus full page contents and highlights.
-
Vector storePinecone
The managed serverless vector database most RAG teams reach for — autoscales to zero, with a control-plane Admin API for programmatic project and key provisioning.
-
Evals & observabilityLangfuse
Open-source LLM engineering platform — tracing, evals, prompt management, and metrics for agent apps.
-
Sandbox / runtimeE2B
Secure cloud sandboxes for running AI-generated code — the runtime layer for code-executing agents.
Embed this stack
The Production-Grade Stack — FAQ
What is Production-Grade Stack?
The observability + safety layer for agents in prod. It pairs LangGraph, OpenRouter, Mem0, Exa, Pinecone, Langfuse, E2B — one tool per job. Teams past the prototype — who need to see, measure, and sandbox what agents do.
Can I change the tools?
Yes — open this stack in the builder and swap any pick, filter by open-source / hosted-API / agent-self-signup, then copy or share the result. Nothing is locked in.
Is it free to use this stack?
The stack, this page, and the builder are free. Each tool has its own pricing, shown on its detail page.
Can an AI agent use this stack?
Yes — it's machine-readable at /api/stack.json?sandbox=e2b, so an agent can request these exact picks (with signup URLs and MCP flags) and act on them.