Open Issues Need Help
View All on GitHub eval: four-outcome taxonomy instead of binary selection accuracy about 4 hours ago
good first issue roadmap leaderboard
Lighthouse for MCP servers — score any MCP server on agent usability, not just spec compliance
TypeScript
eval: held-out task authoring so synthetic tasks can't flatter the schemas that generated them about 4 hours ago
good first issue roadmap leaderboard
Lighthouse for MCP servers — score any MCP server on agent usability, not just spec compliance
TypeScript
eval: pin full environment fingerprint in every result about 4 hours ago
good first issue roadmap leaderboard
Lighthouse for MCP servers — score any MCP server on agent usability, not just spec compliance
TypeScript
docs: production north-star metrics for future correlation study about 4 hours ago
good first issue roadmap leaderboard
Lighthouse for MCP servers — score any MCP server on agent usability, not just spec compliance
TypeScript
leaderboard: stable row anchors, scanned-version column, and a dispute issue template about 4 hours ago
good first issue roadmap leaderboard
Lighthouse for MCP servers — score any MCP server on agent usability, not just spec compliance
TypeScript