An open-source harness for running and evaluating AI agents, with task review workflows, policy guards, cost-based model routing, MCP memory, LangGraph and native engines, evaluation gates, traces, and a local dashboard.
Prices and medians update for the tier you select.
Ranked by how closely each one matches caos-agent-harness's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Market = the products most similar to this one by capability; prices are median / quartiles over its priced members, separated by provider type and buyer tier.