Cursor

Agents

AI-native code editor with integrated agent capabilities and codebase understanding

Most popular AI-native IDE with $400M valuation

Metrics

licensecommercial

providerAnysphere

agent typecoding

base model requirementsclaude-3.5-sonnet, gpt-4o, cursor-small

tool integrations count15

Score Breakdown

adoption92

tool use94

memory context92

self reflection85

planning reasoning88

Compatibility

1111111195 1111111195 1111111192 1111111175

Scoring Methodology

planning_reasoning25% weight

Task decomposition and strategic execution capabilities

Source: AgentBench, WebArena, SWE-bench Verified

tool_use25% weight

Intent recognition, function selection, and execution accuracy

Source: ToolBench, API-Bank, Berkeley Function Calling Leaderboard

memory_context20% weight

Long-context handling and information retention

Source: LongBench, RULER, InfiniteBench

self_reflection15% weight

Error recognition and behavior adjustment

Source: ReAct benchmark, Reflexion evaluation

adoption15% weight

GitHub stars, community usage, ecosystem maturity

Source: GitHub API, PyPI downloads, Stack Overflow activity

Related Signals

Claude Code Leads AI Coding Agent Adoption

Agents1d ago

Claude Code has emerged as the most adopted AI coding agent, with developers citing superior code understanding, autonomous task completion, and seamless IDE integration as key differentiators.

Data Sources

cursor.sh

github.com

Last updated: December 24, 2025