Search: github.com/peak | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: Sour – classic arena FPS in the browser

3 years ago

3 points

62.

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

2 months ago

2 points

63.

Show HN: Meetrics – Track anything, correlate anything, ask your data questions

github.com/sergeybok

3 months ago

2 points

64.

Show HN: Create LLM-optimized random identifiers

github.com/blixt

5 months ago

2 points

65.

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

a year ago

2 points

66.

Show HN: Tarvos – Relay Architecture for infinitely building with coding agents

github.com/Photon48

3 months ago

2 points

67.

Show HN: TurkishSieve CPU/GPU prime sieve found errors in Nicely's tables

github.com/bilgisofttr

4 months ago

2 points

68.

Show HN: Browser-based EEG neurofeedback detecting golden ratio brain coherence

resonate.neurokinetikz.com

4 months ago

2 points

69.

Show HN: SNKV benchmark with RocksDB

github.com/hash-anu

4 months ago

2 points

70.

Show HN: System to have Claude compose and perform a techno track end-to-end

github.com/hughes7370

5 months ago

2 points

71.

Show HN: Enjoy – A gamified GitHub repo where contributions earn karma

github.com/fabriziosalmi

5 months ago

2 points

72.

Running a 270M LLM on Android (architecture and benchmarks)

7 months ago

2 points

73.

A CPU-only demo of ThorVG, a high-performance 2D vector graphics engine

10 months ago

2 points

74.

Show HN: DJ-style audio waveform thumbnailer in Python

github.com/Alzy

a year ago

2 points

75.

NVDSP: High-performance & easy-to-use audio DSP for Novocaine on iOS and OSX

bartolsthoorn.github.com

14 years ago

2 points

76.

Show HN: VizNetGauge, free open source graphical network speed monitor (Windows)

8 years ago

2 points

77.

Show HN: Spotify-style Wrapped for Your Claude/ChatGPT History

7 months ago

1 points

78.

Show HN: Running LLM on smartwatch – found llama.cpp loading model twice in RAM

3 months ago

1 points

79.

Show HN: Lag – Super fast comms (now avail on CLI)

github.com/lag-app

3 months ago

1 points

80.

Show HN: Turkish Sieve Engine – Full Prime Statistics Up to 10^14 and V2 Preview

github.com/bilgisofttr

3 months ago

1 points

81.

Show HN: Chrome extension to export ChatGPT chats, project folders to MD ZIP

github.com/vincze-tamas

4 months ago

1 points

82.

Show HN: PyTorch/FEniCSx pipeline for elastocaloric metamaterial optimization

4 months ago

1 points

83.

Show HN: AdaptGauge – I found that adding few-shot examples can make LLMs worse

github.com/ShuntaroOkuma

4 months ago

1 points

84.

Show HN: Fastdedup – Rust dataset deduplication (2:55 vs. 7:55 688MB vs. 22GB)

wapplewhite4.github.io

4 months ago

1 points

85.

Show HN: OmniGlass – An open-source, sandboxed Visual Action Engine

github.com/goshtasb

4 months ago

1 points

86.

Show HN: OmiAI – A highly opinionated AI SDK with auto-model selection

github.com/JigsawStack

a year ago

1 points

87.

Show HN: Self-hosted family tree web app

github.com/byronka

2 years ago

1 points

88.

Ask HN: Abandoned attempt at interpreter, is this worth anything?

4 years ago

1 points

89.

Ask HN: Cypress.js Based BDD Testing

6 years ago

1 points

90.

Show HN: Apple Health AI ChatBot Using OpenAI API

github.com/nk3750

2 years ago

5 points