Why this exists
New Agent tools ship every month. We keep a ranked shortlist so you can compare coding IDEs, autonomous workers, and research agents without reading every landing page.
How scoring works
Each product is stored as bilingual markdown. The composite score (0–100) blends capability, reliability, ecosystem, and value. Editorial rank is the recommended order on the homepage.
For machines
The same catalog is available over REST and JSON-RPC at /api/mcp, including initialize / tools/list / tools/call.