Hackernews posts about LLM/RAG

1. Show HN: RAGless – similar to RAG, but $0 LLM API costs at runtime (github.com)
   6 points by emilianoc 7 days ago | 8 comments
2. Show HN: Hubmesh – Multi-hop RAG retrieval with zero LLM calls in the query path (github.com)
   3 points by dsk_7699 16 days ago | discuss
3. Offline RAG on iOS with Spatial Integration
   2 points by CartoType about 20 hours ago | 1 comments
4. Ask HN: Should I Combine Global Knowledge, Internet Search, and User RAG
   2 points by abdrhxyiii 25 days ago | 1 comments
5. Show HN: Simple self-hosted LLM assistant with user-steered compounding context (github.com)
   5 points by kol3x 17 days ago | discuss
6. Ask HN: How can I tell which LLM's have been trained on what?
   2 points by RantyDave 13 days ago | 3 comments
7. OSS WebUI Llms.py v4: Projects, Agent Profiles, PDF Studio, RAG (llmspy.org)
   2 points by mythz 7 days ago | discuss
8. Show HN: Grounded-forge: RAG with summaries and task views precomputed at ingest (github.com)
   2 points by chrisgagne 28 days ago | discuss
9. Launch HN: Screenpipe (YC S26) – Record how you work and turn that into agents
   88 points by louis030195 28 days ago | 67 comments
10. Show HN: Mwe-MCP – self-hosted memory for AI agents that knows who may know what (github.com)
    5 points by Fr4nZ82 29 days ago | 1 comments
11. Escaping the LLM Coding Rat Race (aaronstannard.com)
    5 points by Aaronontheweb 23 days ago | 1 comments
12. Escaping the LLM Coding Rat Race (aaronstannard.com)
    1 points by kiyanwang 11 days ago | 1 comments
13. Show HN: Generate domain lists for an LLM to rank (www.uidomains.com)
    1 points by dude3 10 days ago | discuss
14. Run LLM Without OS (www.cnx-software.com)
    3 points by boveyking 21 days ago | 2 comments
15. Agents on Rails: The LLM Benchmark Project (rubyonrails.org)
    4 points by hahahacorn 7 days ago | discuss
16. Agents on Rails: The LLM Benchmark Project (rubyonrails.org)
    1 points by ksec 6 days ago | discuss
17. Evaluating job search ranking with LLM judge (corvi.careers)
    1 points by sp1982 17 days ago | discuss
18. Show HN: Avoiding the Memory Wall by computing LLM inference directly inside RAM
    3 points by pcdeni 29 days ago | discuss
19. Imprint – Fine-tune MoE LLMs bigger than your RAM (github.com)
    2 points by pyeAI 9 days ago | discuss
20. LLM-Shield-Proxy - Zero-Egress PII Proxy for LLM SoC 2 (24MB RAM) (github.com)
    2 points by ninadphalak 17 days ago | discuss
21. Launch HN: OneCLI (YC S26) – OSS sandboxed agent harness for teams (github.com)
    85 points by guyb3 1 day ago | 25 comments
22. I ran the same local LLM on an RTX 5070 laptop and one with an iGPU (www.xda-developers.com)
    3 points by vednig 9 days ago | discuss
23. HN: I ran a 56M parameter LLM across three ESP32-S3 boards via ESP-NOW (github.com)
    2 points by wladimiravila 22 days ago | 2 comments
24. Show HN: Remembrane – agent memory in one SQLite file, zero dependencies (github.com)
    13 points by satyasairay 14 days ago | discuss
25. Show HN: Millwright – Rust-based, self-hosted LLM router (github.com)
    10 points by AndrewLiu96 29 days ago | 7 comments
26. Ask HN: Has your typing gotten worse with AI?
    2 points by aizk 28 days ago | 7 comments
27. Local models head to head for extraction (rakuensoftware.com)
    2 points by jbailes 15 days ago | discuss
28. I asked 6 LLMs to design 100 software systems (opinion-radar.com)
    1 points by mat6661 29 days ago | discuss
29. Measured LLM inference speeds on Apple Silicon, with raw data (CC BY 4.0) (macyou.co)
    13 points by bagdaerdev 24 days ago | 4 comments
30. Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots (cactuscompute.com)
    534 points by HenryNdubuaku 10 days ago | 185 comments