Documentation
Practical rollout guides for Orchestris workspaces, private deployments, model access, usage reporting, and support operations.
Start with the right path
Choose the docs path that matches what you are trying to do now.
Start a Workspace
Create the workspace, connect a provider, and confirm the dashboard looks healthy.
Start a WorkspaceDeploy Privately
Run Orchestris Server as a self-hosted or dedicated managed deployment.
Deploy PrivatelyConnect Models
Give users one place to access OpenAI, Anthropic, Gemini, and internal models.
Connect ModelsBrowse by job
The docs are organized around rollout stages instead of isolated product features.
Start Here
First-run guidance for workspace setup, clients, and readiness checks.
- Getting StartedCreate an account, choose the right deployment path, and get a healthy first workspace online.
- Client InstallationJoin the client waitlist or use an approved early-access client surface for your organization workspace.
- System RequirementsReview the baseline client, server, database, and network requirements before rollout.
Deploy & Configure
Server deployment, environment configuration, licensing, and security defaults.
- Orchestris Server DeploymentDeploy Orchestris Server for private, self-hosted, or dedicated managed environments.
- Configuration GuideConfigure environment variables, licensing, providers, and operational defaults.
- Security SettingsHarden your deployment with identity, key rotation, provider, and audit controls.
Models & Providers
Provider setup, model aliases, private endpoints, and model routing.
- Using AI ModelsHelp users choose the right models without exposing provider complexity.
- OpenAI IntegrationConnect OpenAI models and expose approved options through the provider catalog.
- Anthropic IntegrationConnect Anthropic models for teams that need strong long-context and reasoning workflows.
- Local Model IntegrationConnect llama.cpp, OpenAI-compatible gateways, or other production-ready internal model endpoints.
- Custom ProvidersAdd OpenAI-compatible providers, private gateways, and model routing rules.
Access & Controls
Users, roles, quotas, access policy, and identity planning.
- User ManagementInvite employees, manage account status, and keep access aligned with business roles.
- Access ControlUse roles, quotas, and model availability to keep AI access appropriate for each team.
- Rate Limits and QuotasSet usage limits that protect shared infrastructure and keep AI spend predictable.
- Team Sign-In PlanningPlan identity requirements for private deployments and future enterprise sign-in work.
Operations
Usage reporting, cross-device behavior, performance, and support diagnostics.
- Usage AnalyticsTrack requests, tokens, latency, and estimated cost across users, providers, and models.
- Conversation ManagementHelp users organize work while keeping shared policies and retention expectations clear.
- Multi-device SyncKeep the same workspace, conversations, and model access available across client platforms.
- Performance TipsImprove perceived latency, provider reliability, and private model throughput.
- Debug LogsCollect useful logs and request context for faster support and incident triage.
API & Automation
OpenAI-compatible agent access, REST guidance, and automation planning.
- Agent API GatewayConnect OpenAI-compatible agent tools to Orchestris Server while keeping model access, quota, and usage controls in one place.
- REST APIUse REST endpoints for authentication, licensing, deployments, billing, and operational automation.
- Client Streaming NotesUnderstand the native streaming path used by connected clients and private deployments.
- Webhook NotesPlan webhook-style automation around documented portal and billing events.
- API Integration NotesPlan future SDK usage around stable REST contracts and deployment credentials.
Troubleshooting
Fast paths for common errors, missing models, connectivity, and rate limits.
Popular Topics
High-signal guides for the questions we hear most often.
How do I deploy Orchestris privately?
Provision the server, configure licensing, and verify a healthy deployment.
Read Guide →How do employees choose the right model?
Use the model picker and aliases instead of provider-specific setup.
Read Guide →How should I manage user permissions?
Separate admins from members and keep model access aligned with role.
Read Guide →How do I track AI cost and usage?
Review request, token, latency, and estimated-cost trends across providers.
Read Guide →How do I connect AI agents?
Use the OpenAI-compatible gateway with API keys, model aliases, quotas, and usage tracking.
Read Guide →How do I add private or custom providers?
Register OpenAI-compatible endpoints and route them through stable aliases.
Read Guide →Where should I start troubleshooting?
Check auth, organization membership, provider health, and request IDs first.
Read Guide →Need More Help?
Can't find what you're looking for? Use the docs search or contact support for deployment and account questions.
Search Documentation
Search by task, product area, provider, or error code.
Support Center
Open support resources and contact options for setup, deployment, billing, and rollout questions.
Visit Support