HN Explorer

agentseal

↗ HN profile [ 57.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Eywa: Local-first memory for AI agents, with a receipt for every fact (arxiv.org)
    2 points 1
  2. Where AI coding spend goes: 48% code, 40% thinking (codeburn.app)
    2 points 1
  3. 1 points 1
  4. 1 points 1
  5. Opus 4.7 vs. 4.6 after 3 days of real coding side by side from my actual session

    I spent some time today comparing Opus 4.6 and 4.7 using my own usage data to see how they actually behave side by side. still pretty early for 4.7, but a few things surprised me. In my sessions, 4.7 gets things right…

    16 points 2
  6. 1 points 0
  7. Show HN: CodeBurn – Analyze Claude Code token usage by task (github.com)

    Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens. Tools like ccusage give a cost breakdown per model and per day, but I wanted to…

    112 points 22
  8. 1 points 1
  9. 1 points 0
  10. 1 points 1
  11. 1 points 1
  12. AgentSeal – Security scanner for AI agents (150 attack probes) (github.com)
    1 points 3