Search: github.com/quantfive | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: Airgapped Offline RAG – Run LLMs Locally with Llama, Mistral, & Gemini (github.com/vincentkoc)

9 points

2 years ago

62.

Are Prometheus and Thanos developers against fair competition?

8 points

6 years ago

63.

Show HN: I open-sourced a $1M engine for closing loops in embedding space (github.com/onestardao)

8 points

a year ago

64.

Show HN: Xybrid – run LLM and speech locally in your app (no back end, Rust) (github.com/xybrid-ai)

6 points

3 months ago

65.

Show HN: A tool that turns everyday computers into your own AI cloud (github.com/kalavai-net)

5 points

2 years ago

66.

Show HN: An Autonomous Agent That Runs on Open Source Local LLMs (github.com/Nuggt-dev)

5 points

3 years ago

67.

Show HN: A Zero-Copy 1.58-bit LLM Engine hitting 117 Tokens/s on single CPU core (github.com/r3-engine)

4 points

4 months ago

68.

Show HN: Detecting hallucinations in LLM function calling with entropy (archgw.com)

4 points

honorable_coder

10 months ago

69.

Show HN: Fine-tuning an LLM on your code for better code completions (prvn.sh)

4 points

a year ago

70.

Show HN: Kalosm – a local first AI meta-framework in Rust (github.com/floneum)

4 points

3 years ago

71.

AIs built a working Deleuzian engine and the verification script to prove it

3 points

8 months ago

72.

Show HN: ngrep – grep plus word embeddings (Rust) (github.com/0xNaN)

3 points

3 months ago

73.

Show HN: I built a LLM human rights evaluator for HN (content vs. site behavior) (observatory.unratified.org)

3 points

3 months ago

74.

Ask HN: Discussion on the future of the WWW (and Tent, Bitcoin, etc)

3 points

14 years ago

75.

Show HN: Cachey, a Read-Through Cache for S3 (github.com/s2-streamstore)

3 points

9 months ago

76.

Show HN: Run Unsloth Dynamic GGUFs using Docker model runner (github.com/docker)

3 points

7 months ago

77.

Show HN: Awesome Flux – Open Source repo for FLUX model resources (github.com/Eris2025)

3 points

2 years ago

78.

Show HN: Collider – the platform for local LLM debug and inference at warp speed (github.com/gotzmann)

3 points

3 years ago

79.

Fixed a llama.cpp bug silently disabling Vulkan GPU on all 32-bit ARM devices

3 points

2 months ago

80.

Tq-KV – Rust implementation of TurboQuant that works on GGUF models

3 points

2 months ago

81.

Show HN: A Responsibility-Driven Replacement for ITIL/ITSM(OpenSource,Cap-Based) (github.com/Xtothepowerofinfinity)

3 points

a year ago

82.

Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs

2 points

a month ago

83.

Show HN: Loft CLI – Fine-tune and run LLMs (1–3B) on 8 GB MacBook Air, no GPUs

2 points

10 months ago

84.

Show HN: LlamaFarm – Working on binary AI Project deployment – (early preview) (github.com/llama-farm)

2 points

a year ago

85.

Sumi – Open-source voice-to-text with local AI polishing

2 points

3 months ago

86.

Show HN: Reduction Blockprint Planner/Simulator (reduction-planner.hirson.xyz)

2 points

3 months ago

87.

Show HN: OctoFlow v1.0.0 – GPU VM where the GPU runs autonomously, CPU is BIOS

2 points

3 months ago

88.

Show HN: Local Voice Assistant

2 points

4 months ago

89.

Show HN: Promptscout a local prompt enricher for Claude Code (github.com/obsfx)

2 points

4 months ago

90.

Show HN: TrendScope – Real-time financial sentiment analysis on a cheap VPS (trendscope.akamaar.dev)

2 points

4 months ago