Documentation
Guides and reference documentation
Getting Started
Skills
Skills are reusable, discoverable capabilities that define what agents can do. They replace the former playbook system with structured YAML-based definitions.
Licensing
Understand how systemprompt.io licensing works: the core is BSL-1.1, the template is MIT and fully yours.
Early Access
systemprompt.io is in open early access. Expect quirks—we're committed to fixing every bug and vulnerability you report.
Installation
Clone the systemprompt-template to get a complete running Rust binary with A2A agents, MCP servers, and a static-generated homepage ready to extend.
Coding Standards
Rust coding standards for systemprompt.io - idiomatic patterns, mandatory requirements, and anti-patterns to avoid
Configuration
Runtime Configuration
Environment type, logging levels, output format, and interactive mode settings.
Server Configuration
HTTP server settings including host, port, API URLs, CORS, and HTTPS.
Paths Configuration
Directory paths for system files, services, binaries, and optional storage.
Cloud Credentials
Cloud API authentication credentials, token management, and login workflow.
Security Configuration
JWT token settings including issuer, expiration times, and audience configuration.
Rate Limits
API request throttling with per-endpoint limits and user tier multipliers.
Custom Domains
Configure custom domains for systemprompt.io Cloud with automatic TLS certificates via Let's Encrypt.
Tenants
Isolated environments for systemprompt.io. Local tenants run on your machine, cloud tenants run on managed infrastructure.
Configuration & Credentials
How credentials management works in .systemprompt/ - sessions, tenants, profiles, secrets, and cloud deployment.
Deployment
Deploy AI agents to systemprompt.io Cloud with a single command. CI/CD integration, zero-downtime deployments, and rollback strategies.
Code Sync
Synchronize configuration between local development and systemprompt.io Cloud. Push, pull, and resolve conflicts.
Profiles
Environment configurations for systemprompt.io. Each profile contains all settings needed to run in a specific environment.
Secrets & Credentials
Manage API keys, credentials, and sensitive configuration for local development and cloud deployments.
Sessions
CLI authentication state and profile switching. Sessions track which profile is active and authenticate your requests.
Docker Configuration
Docker serves two purposes in systemprompt.io: running PostgreSQL locally and deploying your application to production.
Database
Configure PostgreSQL database connection for systemprompt.io. One connection string is all you need.
Services
Database Service
Database access patterns in Rust code - connecting to PostgreSQL, using repositories, and accessing the pool in different contexts
Users
Per-user isolation from day one. User scopes enforced automatically across all operations.
Web Service
Reference for the web service that renders pages, manages templates, serves assets, and controls the entire presentation layer of a systemprompt.io application.
Authentication
OAuth2/OIDC authorization, WebAuthn passwordless login, magic link authentication, JWT token lifecycle, and session management built into every layer of systemprompt.io.
MCP Service -- Host and Manage MCP Servers
Host production MCP servers with OAuth authentication, tool discovery, capability negotiation, and streamable HTTP transport. Integrate with Claude Desktop, Claude Code, and any MCP-compatible client.
Skills Service
Skills define reusable agent capabilities in systemprompt.io. They replace the former playbooks system with structured YAML definitions.
Files Service
Three-layer file storage with local and S3 backends, permission-scoped access, upload handling, and CDN-ready serving for AI workloads.
Analytics Service
Automatic tracking of AI costs, usage metrics, session engagement, content performance, and audit trails. Every request logged with full observability.
Content Service
Manage blog posts, documentation, and legal pages with markdown authoring, YAML frontmatter, automatic indexing, and built-in SEO. The content service ingests files, stores them in PostgreSQL, and generates sitemaps, RSS feeds, and llms.txt.
AI Services
Configure and manage AI providers in systemprompt.io. Supports Anthropic, OpenAI, and Google Gemini with streaming, web search grounding, image generation, smart routing, and MCP tool integration.
Config Service
The config service aggregates all service configurations into a unified hub, managing includes, global settings, and startup validation.
Scheduled Jobs
Run background jobs on cron schedules for content publishing, analytics aggregation, session cleanup, database maintenance, and custom automation tasks.
Services
Configure and manage the runtime components that power your systemprompt.io instance - agents, skills, MCP servers, content, AI, scheduled jobs, and web interface.
Skills Service
Define reusable agent capabilities through skills. Skills provide tagged, discoverable actions that multiple agents can share.
Workflows
Define once, execute anywhere. Skills and multi-agent orchestration provide YAML-based automation that both humans and AI agents can run through CLI, MCP, or scheduled jobs.
Agent Services
Configure and orchestrate AI agents with A2A protocol support, skills-based capabilities, multi-agent workflows, and OAuth security. Agents are the AI workers that perform tasks in systemprompt.io.
Guides
Connect MCP Servers
Connect Claude Code, ChatGPT, and other AI clients to your systemprompt MCP servers. OAuth-secured tool access with full audit trail.
Guides
Step-by-step guides to get the most out of your systemprompt.io installation.
Deploy as a Website
Deploy your systemprompt template to production with user authentication, custom domains, and SSL. Ship your AI agents to real users.
Talk to Your Agents
Send HTTP messages to your systemprompt agents and see them respond in real-time. Learn the CLI commands and HTTP endpoints for agent communication.
Extensions
MCP Tool Structure
Detailed reference for organizing tools with modular directory patterns, handler signatures, and schema definitions.
MCP Resources
Implementing MCP resources and templates for exposing data and UI artifacts to clients.
MCP Server AI Integration
Complete guide to integrating AI services (Gemini, Anthropic, OpenAI) into MCP servers with search grounding and artifact persistence.
MCP Response Patterns
Best practices for returning tool results with both human-readable and structured content.
MCP Skill Integration
Loading and using skills in MCP servers for AI-powered tool implementations.
Typed Extensions
Compile-time type-safe extension traits for schema, API, job, provider, and config extensions.
Extension Initialization
How extensions integrate with AppContext during runtime startup.
Extension Discovery
How the runtime discovers and validates extensions at startup.
Extension Builder
Type-safe extension registration with compile-time dependency checking.
Provider Extension
Add LLM and tool providers to your extension.
Content Data Provider
Enrich content items with computed fields, related content, and database lookups.
RSS & Sitemap Providers
Generate RSS feeds and sitemap entries for your content.
Asset Declaration
Declare CSS, JavaScript, fonts, and images for your extension.
Page Prerenderer
Generate static HTML pages at build time for list pages, index pages, and configured content.
Extension Dependencies
Declare and manage dependencies between extensions.
Template Data Extender
Make final modifications to template data after all providers and renderers have run.
Frontmatter Processor
Parse custom frontmatter fields during content ingestion.
Extension Registration
How extensions register with the runtime using the inventory crate and register_extension! macro.
Error Handling
Error types for extension loading, configuration, and runtime.
API Extension
Add HTTP routes and API endpoints to your extension.
Job Extension
Add background jobs and scheduled tasks to your extension.
Schema Extension
Add database schemas and migrations to your extension.
Config Extension
Add configuration namespaces and validation to your extension.
Extension Trait Reference
Complete reference for the Extension trait with all 30+ methods for database, API, jobs, providers, and web rendering.
Page Data Providers
Create PageDataProvider implementations to provide ALL template variables for your pages.
Component Renderers
Create ComponentRenderer implementations to generate HTML fragments for your templates.
Extensions and Scoped Permissions
How systemprompt.io extensions work across four domains, and how permission scoping enforces per-agent, per-tool authorization through OAuth2, roles, and access control rules.
CLI Extensions
Build standalone CLI extensions for custom commands, external integrations, and utility tools that agents can execute via subprocess.
Web Extensions
Build web extensions for page data, static generation, templates, and asset management.
Library Extensions
Build library extensions that compile into the main binary: API routes, database schemas, background jobs, and providers.
MCP Extensions
Build standalone MCP server extensions that expose tools for AI agents via the Model Context Protocol.
Metrics
APM — Actions Per Minute
Understanding the Actions Per Minute metric in the systemprompt.io Control Center
Concurrency — Parallel Session Count
Understanding the Concurrency metric in the systemprompt.io Control Center
Tool Diversity — Unique Tools Used
Understanding the Tool Diversity metric in the systemprompt.io Control Center
Multitasking Score — Delegation & Parallelism
Understanding the Multitasking Score metric in the systemprompt.io Control Center
EAPM — Effective Actions Per Minute
Understanding the Effective Actions Per Minute metric in the systemprompt.io Control Center
Throughput — Data Volume
Understanding the Throughput metric in the systemprompt.io Control Center