Own your AI
infrastructure
A self-hosted, open-source platform for deploying, managing, and scaling conversational AI across your organization. Multi-model. Enterprise-grade. Yours to control.
Why SecondStack
Built for teams that take AI seriously
Self-hosted & open source
Deploy on your infrastructure. Full data sovereignty — no vendor lock-in. MIT licensed and auditable.
Enterprise team management
Per-user and per-team budgets, identity federation with Azure AD and Keycloak, granular model access control.
Multi-model unified gateway
One interface for Anthropic, OpenAI, Google, and local models. Switch providers mid-conversation. No rewiring.
Setup
Up and running in minutes
Three steps from zero to a production AI platform.
Deploy
Clone the repo and run Docker Compose. The full platform spins up with PostgreSQL, Redis, Meilisearch, and authentication — all pre-configured.
# Clone & initialize git clone https://github.com/ SecondStack-AI/SecondStack cd SecondStack ./init_platform.sh
Connect providers
Add your LLM provider API keys through ControlTower. Supports Anthropic, OpenAI, Google Gemini, and local models via vLLM. Configure models, pricing, and capabilities in one place.
Invite your team
Set up teams, assign budgets, and connect your identity provider. Users get instant access to a multi-model chat interface with full cost tracking.
Features
Everything your team needs
A complete conversational AI platform, not just a chat interface.
Multi-model chat
Switch between Claude, GPT, Gemini, and local models mid-conversation. Grouped by capability — chat, reasoning, image generation. Your team picks the right model for each task.
Admin dashboard
Centralized model management, provider configuration, system prompts, and deployment controls. One panel for your entire AI stack.
Models
| Model | Display Name | Access | Status | Health | Order | Actions |
|---|---|---|---|---|---|---|
| claude-sonnet-4-6 | Claude Sonnet 4.6 | All Users | active | 2/2 OK | ||
| claude-opus-4-6 | Claude Opus 4.6 | All Users | active | 3/4 OK | ||
| gpt-4.1 | GPT-4.1 | Engineering | active | 2/2 OK | ||
| gemini-2.5-flash | Gemini 2.5 Flash | All Users | active | 1/1 OK | ||
| agent-claude(agent) | Agent Claude | 2 Teams | active | N/A | ||
| gpt-image-1(image_generation) | GPT Image 1 | Hidden | disabled | — |
Users
| User | Role | Teams | Last Active | Actions | |
|---|---|---|---|---|---|
| JC Jane Chen | jane.chen@acme.com | Admin | Engineering, Platform | 2 min ago | |
| MR Mike Rodriguez | mike.r@acme.com | User | Engineering | 14 min ago | |
| SP Sarah Park | sarah.p@acme.com | User | Design, Marketing | 1 hr ago | |
| AK Alex Kim | alex.kim@acme.com | Manager | Engineering, QA | 3 hrs ago | |
| LW Lisa Wang | lisa.w@acme.com | User | Marketing | 1 day ago |
Providers
Teams
Groups
| Group | Source | Members | Teams | Actions |
|---|---|---|---|---|
| engineering-all | Azure AD | 24 | Engineering, Platform | |
| design-team | Azure AD | 8 | Design | |
| marketing-all | Manual | 12 | Marketing |
Analytics & Logs
| Time | Model | User | Tokens | Latency | Status |
|---|---|---|---|---|---|
| 14:32:01 | claude-sonnet-4-6 | jane.chen | 2,847 | 1.2s | 200 |
| 14:31:58 | gpt-4.1 | mike.r | 1,204 | 0.8s | 200 |
| 14:31:45 | claude-opus-4-6 | alex.kim | 5,102 | 3.4s | 200 |
| 14:31:32 | gemini-2.5-flash | sarah.p | 892 | 0.4s | 200 |
General Config
Notifications
MCP Servers
| Server | Type | Tools | Status | Actions |
|---|---|---|---|---|
| filesystem | stdio | 6 tools | active | |
| web-search | sse | 2 tools | active | |
| database | stdio | 4 tools | degraded |
Guardrails
| Rule | Scope | Action | Status |
|---|---|---|---|
| PII Detection | All Models | Block & Alert | active |
| Prompt Injection | All Models | Block | active |
| Code Execution | Agent Claude | Warn | active |
Localized Content
| Locale | Strings | Coverage | Status |
|---|---|---|---|
| English (en) | 247 | 100% | default |
| German (de) | 241 | 97.6% | active |
| Japanese (ja) | 189 | 76.5% | partial |
Config & Deploy
Budget & spend controls
Per-user, per-team, and per-API-key budgets. Threshold alerts, spend forecasting, and usage analytics down to the request level.
Agentic code execution
Agent Claude runs in sandboxed containers with 50+ skills — file operations, browser automation, image generation, and persistent memory across sessions.
Enterprise identity
Built-in OAuth with Authentik. Federation with Azure AD and Keycloak. Automatic group sync and role-based access control.
Search & retrieval
Meilisearch-powered full-text search across threads and messages. Find any conversation instantly. Document extraction with Docling and Kreuzberg.
Pricing
Open source. Deploy anywhere.
SecondStack is MIT licensed. Run it on your hardware or let us help.
Community
Open source, forever
Full platform for teams getting started with self-hosted AI.
- All platform features
- Docker Compose deployment
- Community support via GitHub
- Multi-model chat interface
- Team & budget management
- Identity federation
Enterprise
Tailored to your needs
For organizations requiring dedicated support and advanced deployment.
- Everything in Community
- Kubernetes deployment support
- Priority support & SLA
- Custom integrations
- Deployment assistance
- Security review & hardening
Which LLM providers does SecondStack support?
How does self-hosting work?
What are the system requirements?
Is SecondStack really free?
How does team and budget management work?
Can I use local models instead of cloud APIs?
Ready to own your AI infrastructure?
Deploy SecondStack in minutes. Open source, self-hosted, and built for teams that demand control.