| layout | home |
|---|---|
| title | SigmOS: Sigma Modular Operating Spec |
A next-generation Domain-Specific Language for AI-native systems
SigmOS is a revolutionary Domain-Specific Language (DSL) that brings declarative-first thinking to AI-native system orchestration. Think of it as the missing piece between configuration files and full programming languages—designed specifically for the era of intelligent, reactive systems.
spec "AIAgent" v1.0 {
description: "An intelligent agent with multimodal capabilities"
inputs:
name: string
personality: enum("helpful", "creative", "analytical")
api_key: string { secret: true }
computed:
greeting: -> "Hello! I'm {{name}}, your {{personality}} AI assistant."
actions:
respond: prompt {
system: "You are a {{personality}} AI assistant named {{name}}."
user: "{{input.message}}"
model: "gpt-4"
}
}
Prompts, LLM inference, and dynamic generation as first-class citizens. Build intelligent systems that think and adapt.
Modular specs, reusable patterns, and namespaced imports. Build complex systems from simple, tested components.
Trigger-based, event-driven, lifecycle-aware systems that respond intelligently to changing conditions.
Field permissioning, trusted imports, and deterministic evaluation keep your systems safe and predictable.
Strong types, constraint logic, and schema compliance ensure your specifications are correct by construction.
Get up and running with SigmOS in minutes:
# Clone the repository
git clone https://github.com/copyleftdev/sigmos.git
cd sigmos
# Build the project
cargo build --release
# Install the CLI
cargo install --path crates/cli
# Run your first spec
sigmos run examples/agent.sigmosSigmOS excels in scenarios where you need to orchestrate intelligent, reactive systems:
- AI Workflow Orchestration: Chain LLM calls, process multimodal data, and handle complex reasoning workflows
- Intelligent Automation: Build systems that adapt and learn from their environment
- API Orchestration: Compose complex API interactions with built-in error handling and retries
- Content Generation Pipelines: Create sophisticated content workflows with AI-powered generation and validation
- Smart System Configuration: Define infrastructure that responds intelligently to changing conditions
Traditional configuration languages weren't designed for the AI era. SigmOS bridges the gap between static configuration and full programming languages, offering:
- Declarative Simplicity: Express what should happen, not how
- AI-First Design: Native support for prompts, models, and intelligent workflows
- Type Safety: Catch errors at specification time, not runtime
- Composability: Build complex systems from simple, reusable components
- Future-Proof: Designed for the next generation of intelligent systems
Join the community building the next generation of intelligent systems.
Get Started Now →