What problem does it solve?
Ecomode minimizes token consumption and inference costs by steering work toward lower-cost model tiers during agent orchestration, reducing unnecessary use of expensive thorough models while preserving quality for critical tasks.
Core Features & Use Cases
- Cost-aware model routing: Prefers LOW-tier agents for most tasks, falls back to STANDARD only when LOW fails, and reserves THOROUGH for essential planning or critique.
- Agent delegation guidance: Provides explicit delegation preferences for executor, explore, architect, planner, and writer roles to optimize cost without changing orchestration rules.
- Operational controls: Supports background execution limits, lifecycle state via forge_state, and can be disabled in user config for full control.
- Use Case: Run large-scale code discovery, documentation, or routine refactors across a repository while significantly reducing token usage and cost.
Quick Start
Activate ecomode in your Forge session to route tasks to LOW-tier agents and reduce token consumption.