Hackernews posts about LLM/RAG

1. Memelang – query language optimized for LLM RAG token efficiency (memelang.net)
   1 points by memelang 26 days ago | discuss
2. Valori – A Python-native Vector Database I built from scratch
   9 points by varshith17 8 days ago | 11 comments
3. Fusing Geoscience LLMs and Lightweight RAG for Geological Question Answering (www.mdpi.com)
   2 points by PaulHoule 19 days ago | discuss
4. Turning Historical Incidents into AI Insights (blog.paypay.ne.jp)
   3 points by qmarchi 19 days ago | discuss
5. Maestro — Graph RAG orchestration engine (FastAPI + React + pgvector)
   1 points by snowypainter 13 days ago | 1 comments
6. Show HN: Vision-Based, Vectorless RAG for Long Douments (github.com)
   6 points by page_index 17 days ago | discuss
7. Show HN: Understanding LLM fundamentals without frameworks (github.com)
   6 points by maxtermed 24 days ago | discuss
8. Show HN: OpenHealth – AI health platform with RAG over 38M medical papers
   3 points by heliosinc 11 days ago | 1 comments
9. Show HN: Dream – An LLM memory architecture using adaptive TTL to control cost
   2 points by matheusdevmp about 16 hours ago | discuss
10. Show HN: Treyspace ─ Open Source Graph RAG on Your Excalidraw Canvas (github.com)
    2 points by lforster about 24 hours ago | discuss
11. Show HN: I built an LLM that never forgets – persistent user memory with RAG (github.com)
    2 points by modinfo 27 days ago | discuss
12. Show HN: Flamehaven FileSearch – Self-Hosted RAG Semantic Search (github.com)
    1 points by Flamehaven 5 days ago | 1 comments
13. Show HN: Inspect Element for LLM Apps (github.com)
    1 points by zombico 26 days ago | 1 comments
14. Show HN: Story Keeper – AI agents with narrative continuity instead of memory (github.com)
    16 points by neurobloom 25 days ago | 4 comments
15. Show HN: Pg_textsearch – BM25 Ranking for Postgres (docs.tigerdata.com)
    13 points by tjgreen 25 days ago | discuss
16. Show HN: Spine AI – Visual workspace to think across multiple AI models (app.getspine.ai)
    11 points by akshay_budhkar 8 days ago | discuss
17. Show HN: MarkdownConverters – Convert any file format to clean Markdown (markdownconverters.com)
    9 points by Dkaur 29 days ago | 5 comments
18. Interview with the lead author of REFRAG (Meta)
    4 points by CShorten 14 days ago | discuss
19. Show HN: inbox.dog – AI agents for Gmail support that sort, reply, and escalate (inbox.dog)
    2 points by acoyfellow 4 days ago | discuss
20. Anyone used Reducto for parsing? How good is their embedding-aware chunking?
    2 points by Bahushruth 23 days ago | discuss
21. Anyone used Reducto for parsing? How good is their embedding-aware chunking?
    2 points by Bahushruth 23 days ago | discuss
22. Show HN: MuseBot–An AI Chatbot for Telegram, Discord, Slack, Lark, QQ, and More (github.com)
    1 points by yincong0822 25 days ago | 1 comments
23. Show HN: Real-Time Emotional Intelligence for E-Commerce: actual signals (sentientiq.ai)
    1 points by sentientiq 21 days ago | discuss
24. Show HN: Extrai – An open-source tool to fight LLM randomness in data extraction (github.com)
    5 points by elias_t 14 days ago | discuss
25. LLM Exchange Rates Updated (arctotherium.substack.com)
    3 points by gmays 24 days ago | discuss
26. Ranking LLMs based on 180k French votes (French government's AI arena) (comparia.beta.gouv.fr)
    2 points by simon-inta 13 days ago | 1 comments
27. Show HN: Anytool – Give your LLM infinite tools with one API (anytoolhq.com)
    2 points by acoyfellow 4 days ago | 6 comments
28. How do LLM's trade off lives between different categories? (arctotherium.substack.com)
    16 points by alexcos 26 days ago | 9 comments
29. Explanation of Gated DeltaNet (Qwen3-Next and Kimi Linear) (github.com)
    3 points by ModelForge 14 days ago | discuss
30. How do LLM's trade off lives between different categories? (arctotherium.substack.com)
    2 points by 015UUZn8aEvW 29 days ago | discuss