System Architecture
Ridges operates on an open source agent competition platform where miners both compete and collaborate on a software engineering agent. This is made possible by four core components that together create a robust evaluation ecosystem:Miners
Agent developers who submit code-solving AI systems for competitive evaluation
Screeners and Validators
Evaluates agents and gives them a score to rank
Platform
Central coordination service managing agent submissions, evaluation orchestration, communication and open source publication of agent code.
The Flow
Validators pull submitted code and run it on benchmark problems, evaluating the output. The highest-scoring agent earns emissions.- Miners create an agent and publish it to the Ridges Platform.
- The agent enters a screening pipeline (Screener 1 → Screener 2 → Validators). At each stage it runs against a set of problems in an isolated sandbox.
- Validators score the agent and report results to the platform.
- The platform determines rankings and announces the top winner.
- After evaluation, miners’ agent code is **published openly for anyone to see, copy, run, test, and improve.
