Hackernews posts about Ollama

1. 01
   

   newNexus-CLI – Pure Go Bridge to DeepSeek R1/V3 with Claude Code and Ollama Supportgithub.com

   ▲ 15xamrayev10d💬 4savesaved
2. 02
   

   newOllama adds local text-to-speech, 100x faster than real time on Apple Siliconollama.com

   ▲ 4abdullahalharir4ddiscusssavesaved
3. 03
   

   newShow HN: Bloby – Clippy on Steroids Chrome Extension Using Chrome AI and Ollamachromewebstore.google.com

   ▲ 3evgy28ddiscusssavesaved
4. 04
   

   newSriti Core – Local-first LLM router that cascades Ollama to cloud to frontiergithub.com

   ▲ 2sudevs29ddiscusssavesaved
5. 05
   

   newShow HN: Ollama Mock Serverollama-mock.kinduff.com

   ▲ 1kinduff36hdiscusssavesaved
6. 06
   

   new2TI Desktop Suite – Rust/Tauri Native Apps (<30MB RAM) with Ollama Perfect Audio2tinteractive.com

   ▲ 1LebToki2ddiscusssavesaved
7. 07
   

   newShow HN: Ollama client library for Golang with streaming API supportgithub.com

   ▲ 1kelthuzad193ddiscusssavesaved
8. 08
   

   newOllama flint requires 0.40.8 but most recent is 0.40.7

   ▲ 1roscas9ddiscusssavesaved
9. 09
   

   newYzma now over 2.6X faster at embeddings than Ollama or Docker Model Runneryzma.ai

   ▲ 1deadprogram11ddiscusssavesaved
10. 10
    

    new2TI LMailer – Native Linux email and groupware (Rust, Tauri v2, local Ollama)2tinteractive.com

    ▲ 1LebToki13ddiscusssavesaved
11. 11
    

    newShow HN: EpochGo – Local-first multi-agent AutoML on Ollama ($0 API costs)github.com

    ▲ 1AryanDinakaran118ddiscusssavesaved
12. 12
    

    newShow HN: Fast Ollama like router that gives a text-only model eyes and earsgithub.com

    ▲ 1djinn29ddiscusssavesaved
13. 13
    

    newShow HN: Apogee: Rebuilding Mozilla's Orbit, fully local and privategithub.com

    ▲ 66zxdc789621d💬 3savesaved
14. 14
    

    newShow HN: Rhun, an open-source code editor written in assemblyrhun.app

    ▲ 64vladcodes29d💬 51savesaved
15. 15
    

    newShow HN: Breadcrumb, record everything on your mac + context manager for AIinnerloop.works

    ▲ 49jv2222229d💬 8savesaved
16. 16
    

    newShow HN: Flash-Agents – DSH as MCP for Claudegithub.com

    ▲ 4tomw180825ddiscusssavesaved
17. 17
    

    newShow HN: Ternlux – Free, local-first, bring-your-own-key AI pipeline builderwww.ternlux.com

    ▲ 3sdataengineer8ddiscusssavesaved
18. 18
    

    newmacOS 27 has a built-in, offline LLM you can call from Terminal

    ▲ 3ymattia9ddiscusssavesaved
19. 19
    

    newShow HN: Putaway – sorts your Mac's Downloads into the folders you havegithub.com

    ▲ 3yashrajpandey14ddiscusssavesaved
20. 20
    

    newJNISleuth-MCP – Recover Stripped JNI Bindings and Ollvm Branches for Ghidra/Ida

    ▲ 3akdapunk17ddiscusssavesaved
21. 21
    

    newShow HN: Wavefunction – a minimal, open-source desktop coding agent for Macwww.wavefunction.si

    ▲ 2spstoyanov38hdiscusssavesaved
22. 22
    

    newShow HN: StrictLLM – For when you need human-in-the-loopstrictllm.com

    ▲ 1StrictLLM38hdiscusssavesaved
23. 23
    

    newHow Improved Voicebot agents now? Does Help Sales and support end to end

    ▲ 1AbhiAmbad6ddiscusssavesaved
24. 24
    

    newShow HN: Long term memory agent for "real world" data workgithub.com

    ▲ 1jad190823ddiscusssavesaved
25. 25
    

    newClef (and Clef Flash) from Cloudflareollama.com

    ▲ 2DerDerDaIst25ddiscusssavesaved
26. 26
    

    newLlama.cpp on a jailbroken PS5: run any GGUF model natively on the consolegithub.com

    ▲ 375Anon8414d💬 89savesaved
27. 27
    

    newLLaMA Now Goes Faster on CPUsjustine.lol

    ▲ 6luu28d💬 3savesaved
28. 28
    

    newNew in Llama.cpp: Decision Modelshuggingface.co

    ▲ 6cuvinny28d💬 1savesaved
29. 29
    

    newExtract v2.5: Rebuilding extraction agents on LlamaParsewww.llamaindex.ai

    ▲ 5cheesyFish29ddiscusssavesaved
30. 30
    

    newSonicBoom – llama.cpp's own kernels, 14% faster decode via a graph compilergithub.com

    ▲ 4nalaginrut17ddiscusssavesaved

· edit