Skip to content
SecondStack SecondStack SecondStack Docs

SecondStack Documentation

Own your AI infrastructure. A self-hosted enterprise AI platform for deploying, managing, and scaling conversational AI across your organization — chat, agents, gateway, guardrails, and budgets, all on your own infrastructure.
What is SecondStack Self-Hosting

SecondStack is a self-hosted enterprise AI platform. It gives your organization one place to run conversational AI — SecondChat, a chat app across Claude, GPT, Gemini, and self-hosted open-weight models; SecondGate, an LLM gateway with virtual keys, budgets, and SecondGuard guardrails; SecondAgent, an agentic AI coworker; Knowledge Collections for RAG; and admin plus user dashboards. Everything runs on infrastructure you control, so conversations, documents, and usage data never leave your environment.

Explore the docs

Section titled “Explore the docs”

Chat & agents

Explore SecondChat, the chat app that spans every provider, and SecondAgent, the agent mode that runs Claude Code in sandboxed containers.

Gateway & controls

Centralize traffic through API Routing, and manage models, providers, and policy from ControlTower.

What the platform includes

Section titled “What the platform includes”
  • SecondChat — the multi-model chat app: image generation, voice input, file attachments, RAG, and agents.
  • Cost Management — per-user, per-team, and per-API-key budgets with threshold alerts and usage analytics.
  • SecondAgent — the agent mode that runs Claude Code in per-thread Docker sandboxes with built-in Skills.
  • Knowledge Collections — named, shareable document sets auto-indexed for retrieval inside any chat.
  • SecondGate — the LLM API gateway with virtual API keys, SecondGuard guardrails, and spend observability.
  • ControlTower — the admin dashboard for models, providers, prompts, guardrails, and access control.
  • User Dashboard — self-service API keys, personal budgets, and per-request usage logs.