Search: github.com/vrza | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

91.

Show HN: AI Council – multi-model deliberation that runs in the browser (github.com/prijak)

5 points

3 months ago

92.

Show HN: I built an AI movie making and design engine in Rust (github.com/storytold)

5 points

4 months ago

93.

Show HN: ClawMem – Open-source agent memory with SOTA local GPU retrieval (github.com/yoloshii)

5 points

2 months ago

94.

TinyTTS: Ultra-light English TTS (9M params, 20MB), 8x CPU, 67x GPU

5 points

3 months ago

95.

Show HN: Clawbernetes – Replace kubectl with conversation (Rust) (github.com/clawbernetes)

5 points

4 months ago

96.

Show HN: Open-source fine-tuning in a Colab notebook (colab.research.google.com)

5 points

2 years ago

97.

Show HN: Self-hosted RAG with MCP support for OpenClaw (github.com/2dogsandanerd)

4 points

4 months ago

98.

Show HN: NSED is public – Mixture-of-Models to Hit SOTA using self-hosted AI (github.com/peeramid-labs)

4 points

4 months ago

99.

Show HN: ArtCraft AI crafting engine, written in Rust (github.com/storytold)

4 points

4 months ago

100.

Show HN: HORenderer3: A C++ software renderer implementing OpenGL 3.3 pipeline (github.com/Hobanghann)

4 points

5 months ago

101.

Run 35B LLMs on Dual Pascal GPUs with QLoRA

4 points

8 months ago

102.

Show HN: A reasoning model that infers over whole tasks in 1ms in latent space (github.com/OrderOneAI)

3 points

a year ago

103.

Show HN: Turn any ComfyUI workflow into a web app or API

3 points

a year ago

104.

Show HN: OctoFlow – A GPU-native programming language

3 points

4 months ago

105.

Seeking Advice on Improving OCR for Watermarked PDFs in My RAG Pipeline

3 points

hundredtrillion

3 months ago

106.

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

3 points

2 months ago

107.

Security Layer 4.0 – First semantic firewall blocks malicious intent"

3 points

6 months ago

108.

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

2 points

a month ago

109.

Why stop at 1M tokens when you can have 10M?

2 points

7 months ago

110.

Show HN: ArtCraft AI crafting engine, written in Rust (github.com/storytold)

2 points

4 months ago

111.

Show HN: MaximusLLM – Train 262k-vocab LLMs on a single 16GB GPU (github.com/yousef-rafat)

2 points

3 months ago

112.

Show HN: From Claude Code to OpenCode – My Evolution in Vibe AI Engineering

2 points

3 months ago

113.

Show HN: Kiln – WebGPU-native out-of-core volume rendering for multi-GB datasets (github.com/MPanknin)

2 points

3 months ago

114.

Show HN: Dia-Jax – A Jax port of the Dia text-to-speech dialogue model (github.com/jaco-bro)

2 points

a year ago

115.

Show HN: Open-source, cross platform document data extraction with no OCR (github.com/NanoNets)

2 points

a year ago

116.

How do I set up my own GPT search assistant?

2 points

3 years ago

117.

A small tool I made for local LLMs: LLM-neofetch-plus

1 point

3 months ago

118.

Show HN: Turkish Sieve Engine – Reaching 1.1T-Items/S on a Single GPU (github.com/bilgisofttr)

1 point

4 months ago

119.

Show HN: AI Tools in Interviews: Leveling the Field or Breaking It? (github.com/nonymous911)

1 point

a year ago

120.

Local Model Router: Ollama/OpenAI-compat bridges for local LLMs via llama.cpp

1 point

2 months ago