Starred repositories
🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.
SS2025 — ✨ Personal site & portfolio for creative developer Henry Desroches
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A TTS model capable of generating ultra-realistic dialogue in one pass.
kawadi is my collection of tools, that I need more frequently
NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
🌳 A type-safe HTML template engine for Python. Build dynamic web pages using Python components with a React-like approach.
Official inference framework for 1-bit LLMs
https://textbehindimage.rexanwong.xyz - create text behind image designs easily
Affiliates - Jekyll Blogging Theme for Affiliate Marketers
Data and information related to the Books3 dataset included as part of The Pile, and used to train Meta's LLaMA among others
A Tailwind 3 starter blog for Hugo
Can you create something cool without modern tools?
We write your reusable computer vision tools. 💜
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
🤫 Noiseless Browsing – Content Blocker for Safari
A coding agent for open models like Kimi K3
Sandstorm is a self-hostable web productivity suite. It's implemented as a security-hardened web app package manager. | Actively sponsored by our friends at TestMu AI
QR designer web app with a novel method of designing qr codes that does not take advantage of error correction
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
PECOS - Prediction for Enormous and Correlated Spaces
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.