Overview
AI orchestration layer that routes development work across multiple LLM providers.
Si · Silicon
Soma is the intelligence layer. It orchestrates multiple AI providers (Claude, GPT, DeepSeek, local models) into workflows that automate development tasks while respecting cost and rate-limit budgets.
Documentation in progress
This section is not yet published. The list below describes the planned scope.
Planned scope
- Workflow definitions and the YAML schema
- Providers and agents (Claude, DeepSeek, GPT, Claude Code, Qwen Code)
- Budgets and rate-limit awareness
- Git-aware context injection
- Workspace integration