Hackernews posts about LLM/RAG

1. Show HN: Nexa-gauge – Cache/cost-aware graph-based eval for LLM and RAG (github.com)
   3 points by Sardhendu 14 days ago | discuss
2. Structured planning, execution, and memory for LLM agents (ragbits 1.6) (deepsense.ai)
   2 points by Applied_AI 29 days ago | discuss
3. I'm looking for an AI Automation Engineer role or gig
   4 points by Divinz 18 days ago | 1 comments
4. Show HN: Ragnerock, an AI data analysis tool (www.ragnerock.com)
   13 points by mmahowald27 24 days ago | 4 comments
5. Show HN: Local RAG Pipeline with Weaviate and Ollama (www.storyblok.com)
   2 points by edodusi 25 days ago | discuss
6. Show HN: Agent MCP Studio – build multi-agent MCP systems in a browser tab (www.agentmcp.studio)
   11 points by stealthtsdb 28 days ago | 6 comments
7. Show HN: An agent that tunes its own cache
   7 points by kaliades 14 days ago | discuss
8. Ask HN: Anyone using AI agents for active learning sprints? Here's my setup
   4 points by bhagyeshsp 23 days ago | 4 comments
9. Show HN: Sentient OS – On-device intelligence layer for your entire digital life (sentient-os.ai)
   3 points by TechExpert2910 20 days ago | 2 comments
10. Train-Before-Test: One Simple Fix That Makes LLM Benchmark Rankings Agree (ghzhang233.github.io)
    2 points by taegee 29 days ago | 1 comments
11. Predicting Rare LLM Failures with 30× Fewer Rollouts (www.lesswrong.com)
    2 points by aranguri 9 days ago | discuss
12. Ask HN: Is the ongoing AI research driving LLM models to be better?
    3 points by thiago_fm 30 days ago | 4 comments
13. Evaluating job search ranking with LLM judged NDCG (corvi.careers)
    1 points by sp1982 3 days ago | discuss
14. Show HN: how I fixed my ai goose tutor to stop punishing understanding (professorgoose.com)
    3 points by zapseo 2 days ago | 2 comments
15. Show HN: Find the best local LLM for your hardware, ranked by benchmarks (github.com)
    283 points by andyyyy64 7 days ago | 68 comments
16. Raspberry Pi 5 gets LLM smarts with AI HAT+ 2 (www.theregister.com)
    4 points by barqawiz 21 days ago | discuss
17. Rars: a Rust RAR implementation, mostly written by LLMs (bitplane.net)
    94 points by davidsong 9 days ago | 84 comments
18. We ran OWASP attacks on 8 LLMs. Optimized small models beat frontier defaults (www.megacode.ai)
    4 points by ChanwooSong 16 days ago | discuss
19. Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (github.com)
    673 points by zambelli 3 days ago | 247 comments
20. Show HN: Sigma Guard – deterministic contradiction checks for graph memory
    3 points by invariantjason 13 days ago | discuss
21. Show HN: I built Male Hormone Lab Interpreter that does what LLMs can't (www.longevity-tools.com)
    2 points by zsolt224 20 days ago | discuss
22. Ask HN: How do you feel about AI assisted blogging?
    5 points by throwarayes 21 days ago | 7 comments
23. Show HN: Zenflow a multi-agent orchestration and workflow engine (github.com)
    2 points by vietanh85 8 days ago | discuss
24. Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git) (github.com)
    260 points by najmuzzaman 27 days ago | 115 comments
25. Show HN: Browser Harness – Gives LLM freedom to complete any browser task (github.com)
    134 points by gregpr07 28 days ago | 66 comments
26. Show HN: Torrix, self hosted, LLM Observability,(no Postgres, no Redis) (github.com)
    74 points by AdarshRao23 9 days ago | 4 comments
27. Show HN: A new benchmark for testing LLMs for deterministic outputs (interfaze.ai)
    60 points by khurdula 23 days ago | 30 comments
28. Show HN: LLMs consume 5.4x less mobile energy than ad-supported web search (dupr.at)
    19 points by duprat 27 days ago | 1 comments
29. Show HN: LocalLLM – Recipes for Running the Local LLM (Need Contributors) (locallllm.fly.dev)
    16 points by Igor_Wiwi 29 days ago | 2 comments
30. Show HN: How to analyze your LLM output – A behavioural health monitor for LLMs (splabs.io)
    10 points by k-thimmaraju 3 days ago | 6 comments