Coverage (30d)
106vs0
This Week
24vs0
Evidence
1 articlesRelationships
0Timeline
Claude Code2026-07-16
Claude Code achieves 80.8% on SWE-Bench with deterministic hooks and verification layers
Claude Code2026-07-13
Claude Code achieves 80.8% SWE-Bench Verified score with 1M token context window
Claude Code2026-07-12
Claude Code launched as an agent runtime with hooks, MCP, and memory for DevOps safety
Claude Code2026-07-10
Claude Code transitions from coding assistant to agent runtime with focus on debugging and tool access
Claude Code2026-07-08
Topped JetBrains Kotlin Benchmark with 85.71% score using Opus 4.7 xhigh
Claude Code2026-07-02
Technique documented for using CLAUDE.md with decision matrices to reduce migration errors
MemPalace2026-04-10
Open-source AI memory system MemPalace launched and achieved 96.6% on LongMemEval benchmark, the highest local-only score ever recorded.
MemPalace2026-04-10
MemPalace reached 35,000 GitHub stars in five days following its launch.
Ecosystem
Claude Code
usesModel Context Protocol76 src
usesGitHub13 src
usesClaude Opus 4.613 src
competes withCursor13 src
competes withGitHub Copilot12 src
usesCLAUDE.md9 src
MemPalace
No mapped relationships
Benchmarks
swe-pro
Claude Code69.2
MemPalace—
terminal-2
Claude Code78.9
MemPalace—
swe-verified
Claude Code88.6
MemPalace—