Search: github.com/tnfe | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

841.

Built a 1.3M-line agent-native OS in Rust while homeless. What now?

3 months ago

11 points

842.

Show HN: WFGY – A reasoning engine that repairs LLM logic without retraining

github.com/onestardao

a year ago

11 points

843.

Show HN: Anthropic's MCP Server Directory

2 years ago

11 points

844.

Show HN: Using LLMs and Embeddings to classify application errors

github.com/highlight

3 years ago

11 points

845.

Show HN: JS Local-only AI Apps starter kit: cost $0 to run and test locally

github.com/ykhli

3 years ago

11 points

846.

Show HN: VDP – open-source unstructured visual data ETL

github.com/instill-ai

4 years ago

11 points

847.

Show HN: STT –> LLM –> TTS pipeline in C

github.com/RhinoDevel

9 months ago

11 points

848.

Show HN: Llama2.c on a Commodore C64

github.com/trholding

a year ago

10 points

849.

Show HN: Privatemode AI

a year ago

10 points

850.

Show HN: LettuceDetect – Lightweight hallucination detector for RAG pipelines

github.com/KRLabsOrg

a year ago

10 points

851.

Show HN: Otto-m8 – A low code AI/ML API deployment Platform

github.com/farhan0167

2 years ago

10 points

852.

Show HN: ColiVara – State of the Art RAG API with Vision Models

github.com/tjmlabs

2 years ago

10 points

853.

Show HN: Gradio Notebook– Notebook UX for Generative AI models in Hugging Face

2 years ago

9 points

854.

Show HN: Model Tools Protocol (MTP) – Forget MCP, bash is all you need

github.com/modeltoolsprotocol

4 months ago

9 points

855.

Show HN: Model2Vec: make sentence transformers 500x faster on CPU, 15x smaller

github.com/MinishLab

2 years ago

9 points

856.

Show HN: USearch Images demo in 200 lines of Python

usearch-images.com

3 years ago

9 points

857.

Show HN: Airgapped Offline RAG – Run LLMs Locally with Llama, Mistral, & Gemini

github.com/vincentkoc

2 years ago

9 points

858.

Show HN: I'm building a simple way to package, collaborate, and deploy ML models

2 years ago

9 points

859.

Show HN: Notation – Bridging infrastructure and runtime code

github.com/notation-dev

2 years ago

9 points

860.

Show HN: Moondream, a small vision language model that runs on 8GB of RAM

github.com/vikhyat

2 years ago

9 points

861.

(ROCm) AMD-GPU-Boost: Unlock Full Performance on Consumer AMD GPUs

10 months ago

8 points

862.

Story of How Im Running an Unlimited $6/Month AI Provider on 4x RTX 3090s

11 days ago

8 points

863.

Show HN: OpenEvolve – open-source implementation of DeepMind's AlphaEvolve

a year ago

8 points

864.

Show HN: Eatmydata.ai – Local-First Question-to-SQL-to-Dashboard AI

15 days ago

8 points

865.

Show HN: MetaBrain – A local document memory for AI agents

23 days ago

8 points

866.

Show HN: Llm.sql – Run a 640MB LLM on SQLite, with 210MB peak RSS and 7.4 tok/s

2 months ago

8 points

867.

Show HN: Unsloth Studio - Local Fine-tuning, Chat UI

github.com/unslothai

3 months ago

8 points

868.

Show HN: Run an Agent Council of LLMs that debate and synthesize answers

github.com/JitseLambrichts

3 months ago

JitseLambrichts

8 points

869.

Show HN: Experiment ▴ LLM UI for developers with tool use visualization

github.com/actualwitch

a year ago

8 points

870.

Show HN: Ktop – a themed terminal system monitor with charts and OOM tracking

github.com/brontoguana

4 months ago

8 points