HN Explorer

Arindam1729

↗ HN profile [ 81.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. Completion Rate Is a Vanity Metric (formaly.io)
    2 points 0
  4. Forms Are Not Dead, Static Forms Are Overused (formaly.io)
    2 points 1
  5. 1 points 0
  6. Vercel Analytics Alternative When You Outgrow the Free Tier (raah.dev)
    1 points 0
  7. 1 points 0
  8. I built a local dashboard to inspect Claude Code sessions, tokens, and costs (github.com)
    1 points 0
  9. Show HN: Cc-Lens, Open Source Analytics Dashboard for Claude Code (github.com)
    3 points 0
  10. We ran 21 MCP database tasks on Claude Sonnet 4.6 (insforge.dev)
    2 points 0
  11. GPT-5.3 Codex vs. Claude Opus 4.6 (tensorlake.ai)
    2 points 0
  12. Using AI for Code Reviews: What Works, What Doesn't, and Why (entelligence.ai)
    3 points 0
  13. Notes after testing OpenAI's Codex App on real execution tasks (tensorlake.ai)
    2 points 0
  14. We Cut Token Usage by 83% and Still Hit 90%+ Retrieval Precision (byterover.dev)
    8 points 4
  15. The Next Enterprise Platform Isn't Data-Driven, It's Context-Driven (tensorlake.ai)
    2 points 1
  16. AI's trillion-dollar opportunity: Context graphs (foundationcapital.com)
    1 points 0
  17. Gemini 3 vs. GPT-5.2: Detailed Coding Comparison (tensorlake.ai)
    2 points 0
  18. 1 points 0
  19. Agent Knowledge Needs More Than Just RAG

    When people talk about “knowledge for agents,” it almost always collapses into RAG. But knowledge can, and should—be treated as a first-class runtime tool, not just a context filler. In most implementations, knowledge…

    3 points 2
  20. Failing to Understand the Exponential, Again (julian.ac)
    7 points 1
  21. 1 points 0
  22. Everyone's trying vectors and graphs for AI memory. We went back to SQL

    When we first started building with LLMs, the gap was obvious: they could reason well in the moment, but forgot everything as soon as the conversation moved on. You could tell an agent, “I don’t like coffee,” and three…

    136 points 26
  23. 1 points 0
  24. 1 points 1
  25. Show HN: Memori – Open-Source Memory Engine for AI Agents (github.com)

    Hey HN! I'm Arindam, part of the team behind Memori (https://memori.gibsonai.com/). Memori adds a stateful memory engine to AI agents, enabling them to stay consistent, recall past work, and improve over time. With…

    17 points 9